2022
- URLBibTeXEndNoteDOIMoustakas, A. Kloukiniotis, A. Papandreou, A. Lalos, P. Kapsalas, and D.-V. Nguyen; K. CarlaScenes: A Synthetic Dataset for Odometry in Autonomous Driving. Zenodo, 2022, Zenodo, 2022. doi:10.5281/zenodo.6672923.
@proceedings{kloukiniotis_andreas_2022_6672923,
author = {Moustakas, A. Kloukiniotis and Papandreou, A. and Lalos, A. and Kapsalas, P. and K., D.-V. Nguyen;},
keywords = {cybersecurity},
month = {jun},
publisher = {Zenodo},
title = {CarlaScenes: A Synthetic Dataset for Odometry in Autonomous Driving},
year = 2022
}%0 Conference Proceedings
%1 kloukiniotis_andreas_2022_6672923
%A Moustakas, A. Kloukiniotis
%A Papandreou, A.
%A Lalos, A.
%A Kapsalas, P.
%A K., D.-V. Nguyen;
%D 2022
%I Zenodo
%R 10.5281/zenodo.6672923
%T CarlaScenes: A Synthetic Dataset for Odometry in Autonomous Driving
%U https://doi.org/10.5281/zenodo.6672923 - BibTeXEndNoteKamal, Mohsin, Christos Kyrkou, Nikos Piperigkos, Andreas Papandreou, Andreas Kloukiniotis, Jordi Casademont, Natalia Porras Mateu, Daniel Banos Castillo, Rodrigo Diaz Rodriguez, Nicola Gregorio Durante, Peter Hofmann, Petros Kapsalas, Aris Lalos, Konstantinos Moustakas, Christos Laoudias, Theocharis Theocharides, and Georgios Ellinas. “A Comprehensive Solution for Securing Connected and Autonomous Vehicles” (2022).
@article{noauthororeditor2022comprehensive,
author = {Kamal, Mohsin and Kyrkou, Christos and Piperigkos, Nikos and Papandreou, Andreas and Kloukiniotis, Andreas and Casademont, Jordi and Porras Mateu, Natalia and Banos Castillo, Daniel and Diaz Rodriguez, Rodrigo and Durante, Nicola Gregorio and Hofmann, Peter and Kapsalas, Petros and Lalos, Aris and Moustakas, Konstantinos and Laoudias, Christos and Theocharides, Theocharis and Ellinas, Georgios},
keywords = {cybersecurity},
title = {A Comprehensive Solution for Securing Connected and Autonomous Vehicles},
year = 2022
}%0 Journal Article
%1 noauthororeditor2022comprehensive
%A Kamal, Mohsin
%A Kyrkou, Christos
%A Piperigkos, Nikos
%A Papandreou, Andreas
%A Kloukiniotis, Andreas
%A Casademont, Jordi
%A Porras Mateu, Natalia
%A Banos Castillo, Daniel
%A Diaz Rodriguez, Rodrigo
%A Durante, Nicola Gregorio
%A Hofmann, Peter
%A Kapsalas, Petros
%A Lalos, Aris
%A Moustakas, Konstantinos
%A Laoudias, Christos
%A Theocharides, Theocharis
%A Ellinas, Georgios
%D 2022
%T A Comprehensive Solution for Securing Connected and Autonomous Vehicles - AbstractURLBibTeXEndNoteDOIKloukiniotis, A., A. Papandreou, A. Lalos, P. Kapsalas, D.-V. Nguyen, and K. Moustakas. “Countering Adversarial Attacks on Autonomous Vehicles Using Denoising Techniques: A Review”. IEEE Open Journal of Intelligent Transportation Systems 3 (2022): 61–80. doi:10.1109/OJITS.2022.3142612.The evolution of automotive technology will eventually permit the automated driving system on the vehicle to handle all circumstances. Human occupants will be just passengers. This poses security issues that need to be addressed. This paper has two aims. The first one investigates strategies for robustifying scene analysis of adversarial road scenes. A taxonomy of the defense mechanisms for countering adversarial perturbations is initially presented, classifying those mechanisms in three major categories: those that modify the data, those that propose adding extra models, and those that focus on modifying the models deployed for scene analysis. Motivated by the limited number of surveys in the first category, we further analyze the approaches that utilize input transformation operations as countermeasures, further classifying them in supervised and unsupervised methods and highlighting both their strengths and weaknesses. The second aim of this paper is to publish CarlaScenes dataset produced using the CARLA simulator. An extensive evaluation study, on CarlaScenes, is performed testing the supervised deep learning approaches that have been either proposed for image restoration or adversarial noise removal. The study presents insights on the robustness of the aforementioned approaches in mitigating adversarial attacks in scene analysis operations.
@article{9678365,
abstract = {The evolution of automotive technology will eventually permit the automated driving system on the vehicle to handle all circumstances. Human occupants will be just passengers. This poses security issues that need to be addressed. This paper has two aims. The first one investigates strategies for robustifying scene analysis of adversarial road scenes. A taxonomy of the defense mechanisms for countering adversarial perturbations is initially presented, classifying those mechanisms in three major categories: those that modify the data, those that propose adding extra models, and those that focus on modifying the models deployed for scene analysis. Motivated by the limited number of surveys in the first category, we further analyze the approaches that utilize input transformation operations as countermeasures, further classifying them in supervised and unsupervised methods and highlighting both their strengths and weaknesses. The second aim of this paper is to publish CarlaScenes dataset produced using the CARLA simulator. An extensive evaluation study, on CarlaScenes, is performed testing the supervised deep learning approaches that have been either proposed for image restoration or adversarial noise removal. The study presents insights on the robustness of the aforementioned approaches in mitigating adversarial attacks in scene analysis operations.},
author = {Kloukiniotis, A. and Papandreou, A. and Lalos, A. and Kapsalas, P. and Nguyen, D.-V. and Moustakas, K.},
journal = {IEEE Open Journal of Intelligent Transportation Systems},
keywords = {cybersecurity},
pages = {61-80},
title = {Countering Adversarial Attacks on Autonomous Vehicles Using Denoising Techniques: A Review},
volume = 3,
year = 2022
}%0 Journal Article
%1 9678365
%A Kloukiniotis, A.
%A Papandreou, A.
%A Lalos, A.
%A Kapsalas, P.
%A Nguyen, D.-V.
%A Moustakas, K.
%D 2022
%J IEEE Open Journal of Intelligent Transportation Systems
%P 61-80
%R 10.1109/OJITS.2022.3142612
%T Countering Adversarial Attacks on Autonomous Vehicles Using Denoising Techniques: A Review
%U https://ieeexplore.ieee.org/document/9678365/
%V 3
%X The evolution of automotive technology will eventually permit the automated driving system on the vehicle to handle all circumstances. Human occupants will be just passengers. This poses security issues that need to be addressed. This paper has two aims. The first one investigates strategies for robustifying scene analysis of adversarial road scenes. A taxonomy of the defense mechanisms for countering adversarial perturbations is initially presented, classifying those mechanisms in three major categories: those that modify the data, those that propose adding extra models, and those that focus on modifying the models deployed for scene analysis. Motivated by the limited number of surveys in the first category, we further analyze the approaches that utilize input transformation operations as countermeasures, further classifying them in supervised and unsupervised methods and highlighting both their strengths and weaknesses. The second aim of this paper is to publish CarlaScenes dataset produced using the CARLA simulator. An extensive evaluation study, on CarlaScenes, is performed testing the supervised deep learning approaches that have been either proposed for image restoration or adversarial noise removal. The study presents insights on the robustness of the aforementioned approaches in mitigating adversarial attacks in scene analysis operations.
2021
- AbstractURLBibTeXEndNoteDOIPino, Adrián, Pouria Khodashenas, Xavier Hesselbach, Estefanía Coronado, and Shuaib Siddiqui. “Validation and Benchmarking of CNFs in OSM for Pure Cloud Native Applications in 5G and Beyond”. In 2021 International Conference on Computer Communications and Networks (ICCCN), 1–9. doi:10.1109/ICCCN52240.2021.9522356.Cloud Native (CN) in 5G systems has been identified as a pivotal candidate for operational and capital expenditure savings as well as for improvements in system agility and services role-out. CN telco is a step forward with respect to Network Function Virtualisation (NFV) aiming at embracing a microservice-based architecture. With this in mind, the European Telecommunications Standards Institute (ETSI) has evolved the ETSI NFV reference architecture to adapt to CN and fill the gap with the NFV framework, including containers and ZeroTouch, among other capabilities. Open-source Management & Orchestration (MANO) initiatives, such as Open Source MANO (OSM), are promoting this adoption giving support to CN solutions based on containers. However, at this early stage deployments are currently non-standalone and embedded in VNF-based solutions such as OpenStack. In this context, this paper presents a proof of concept of a full container technology deployment -via Kubernetes- in a NFV architecture. First, a full CN NFV environment is set with the help of OSM MANO, for which we describe the implementation to enable native kubernetes-based Container Network Functions (CNFs) and analyse their performance, limits, advantages and drawbacks. Finally, our solution for CNFs is benchmarked against a typical OSMOpenStack setup where VNFs are deployed. The results obtained in this work can help to further encourage users and operators to use CNFs and get the most out of containerisation in NFV.
@inproceedings{9522356,
abstract = {Cloud Native (CN) in 5G systems has been identified as a pivotal candidate for operational and capital expenditure savings as well as for improvements in system agility and services role-out. CN telco is a step forward with respect to Network Function Virtualisation (NFV) aiming at embracing a microservice-based architecture. With this in mind, the European Telecommunications Standards Institute (ETSI) has evolved the ETSI NFV reference architecture to adapt to CN and fill the gap with the NFV framework, including containers and ZeroTouch, among other capabilities. Open-source Management & Orchestration (MANO) initiatives, such as Open Source MANO (OSM), are promoting this adoption giving support to CN solutions based on containers. However, at this early stage deployments are currently non-standalone and embedded in VNF-based solutions such as OpenStack. In this context, this paper presents a proof of concept of a full container technology deployment -via Kubernetes- in a NFV architecture. First, a full CN NFV environment is set with the help of OSM MANO, for which we describe the implementation to enable native kubernetes-based Container Network Functions (CNFs) and analyse their performance, limits, advantages and drawbacks. Finally, our solution for CNFs is benchmarked against a typical OSMOpenStack setup where VNFs are deployed. The results obtained in this work can help to further encourage users and operators to use CNFs and get the most out of containerisation in NFV.},
author = {Pino, Adrián and Khodashenas, Pouria and Hesselbach, Xavier and Coronado, Estefanía and Siddiqui, Shuaib},
booktitle = {2021 International Conference on Computer Communications and Networks (ICCCN)},
keywords = {cybersecurity},
month = {July},
pages = {1-9},
title = {Validation and Benchmarking of CNFs in OSM for pure Cloud Native applications in 5G and beyond},
year = 2021
}%0 Conference Paper
%1 9522356
%A Pino, Adrián
%A Khodashenas, Pouria
%A Hesselbach, Xavier
%A Coronado, Estefanía
%A Siddiqui, Shuaib
%B 2021 International Conference on Computer Communications and Networks (ICCCN)
%D 2021
%P 1-9
%R 10.1109/ICCCN52240.2021.9522356
%T Validation and Benchmarking of CNFs in OSM for pure Cloud Native applications in 5G and beyond
%U https://ieeexplore.ieee.org/document/9522356/
%X Cloud Native (CN) in 5G systems has been identified as a pivotal candidate for operational and capital expenditure savings as well as for improvements in system agility and services role-out. CN telco is a step forward with respect to Network Function Virtualisation (NFV) aiming at embracing a microservice-based architecture. With this in mind, the European Telecommunications Standards Institute (ETSI) has evolved the ETSI NFV reference architecture to adapt to CN and fill the gap with the NFV framework, including containers and ZeroTouch, among other capabilities. Open-source Management & Orchestration (MANO) initiatives, such as Open Source MANO (OSM), are promoting this adoption giving support to CN solutions based on containers. However, at this early stage deployments are currently non-standalone and embedded in VNF-based solutions such as OpenStack. In this context, this paper presents a proof of concept of a full container technology deployment -via Kubernetes- in a NFV architecture. First, a full CN NFV environment is set with the help of OSM MANO, for which we describe the implementation to enable native kubernetes-based Container Network Functions (CNFs) and analyse their performance, limits, advantages and drawbacks. Finally, our solution for CNFs is benchmarked against a typical OSMOpenStack setup where VNFs are deployed. The results obtained in this work can help to further encourage users and operators to use CNFs and get the most out of containerisation in NFV. - AbstractURLBibTeXEndNoteDOISiniosoglou, Ilias, Panagiotis Sarigiannidis, Yannis Spyridis, Anish Khadka, Georgios Efstathopoulos, and Thomas Lagkas. “Synthetic Traffic Signs Dataset for Traffic Sign Detection & Recognition In Distributed Smart Systems”. In 2021 17th International Conference on Distributed Computing in Sensor Systems (DCOSS), 302–308. doi:10.1109/DCOSS52077.2021.00056.Traffic sign recognition (TSR) is a key aspect involved in the development of robust automated transportation systems. It inherently involves the task of traffic sign detection (TSD), which can be challenging due to traffic signs often being subject to deterioration or occlusion, caused by various environmental factors, or through actions of vandalism. Even though, notable advancements have been achieved in the areas of TSR and TSD, few studies have provided robust algorithms, able to be generalized in real-world applications. This mostly stems from the lack of an extensive traffic sign dataset, standardized for benchmarking purposes. In light of the aforementioned, this paper presents a novel traffic sign dataset, which consists of the Carla Traffic Sign Detection (CTSD), and the Carla Traffic Sign Recognition Dataset (CATERED), targeting the detection and recognition processes respectively. Using the proposed dataset for training and evaluation, a deep Auto-Encoder algorithm is presented, demonstrating high accuracy in detecting and recognizing the distorted traffic signs. Finally, the system is further extended to a federated learning environment, exemplifying its applicability in modern decentralized and interconnected architectures.
@inproceedings{9600064,
abstract = {Traffic sign recognition (TSR) is a key aspect involved in the development of robust automated transportation systems. It inherently involves the task of traffic sign detection (TSD), which can be challenging due to traffic signs often being subject to deterioration or occlusion, caused by various environmental factors, or through actions of vandalism. Even though, notable advancements have been achieved in the areas of TSR and TSD, few studies have provided robust algorithms, able to be generalized in real-world applications. This mostly stems from the lack of an extensive traffic sign dataset, standardized for benchmarking purposes. In light of the aforementioned, this paper presents a novel traffic sign dataset, which consists of the Carla Traffic Sign Detection (CTSD), and the Carla Traffic Sign Recognition Dataset (CATERED), targeting the detection and recognition processes respectively. Using the proposed dataset for training and evaluation, a deep Auto-Encoder algorithm is presented, demonstrating high accuracy in detecting and recognizing the distorted traffic signs. Finally, the system is further extended to a federated learning environment, exemplifying its applicability in modern decentralized and interconnected architectures.},
author = {Siniosoglou, Ilias and Sarigiannidis, Panagiotis and Spyridis, Yannis and Khadka, Anish and Efstathopoulos, Georgios and Lagkas, Thomas},
booktitle = {2021 17th International Conference on Distributed Computing in Sensor Systems (DCOSS)},
keywords = {cybersecurity},
month = {July},
pages = {302-308},
title = {Synthetic Traffic Signs Dataset for Traffic Sign Detection & Recognition In Distributed Smart Systems},
year = 2021
}%0 Conference Paper
%1 9600064
%A Siniosoglou, Ilias
%A Sarigiannidis, Panagiotis
%A Spyridis, Yannis
%A Khadka, Anish
%A Efstathopoulos, Georgios
%A Lagkas, Thomas
%B 2021 17th International Conference on Distributed Computing in Sensor Systems (DCOSS)
%D 2021
%P 302-308
%R 10.1109/DCOSS52077.2021.00056
%T Synthetic Traffic Signs Dataset for Traffic Sign Detection & Recognition In Distributed Smart Systems
%U https://ieeexplore.ieee.org/document/9600064/
%X Traffic sign recognition (TSR) is a key aspect involved in the development of robust automated transportation systems. It inherently involves the task of traffic sign detection (TSD), which can be challenging due to traffic signs often being subject to deterioration or occlusion, caused by various environmental factors, or through actions of vandalism. Even though, notable advancements have been achieved in the areas of TSR and TSD, few studies have provided robust algorithms, able to be generalized in real-world applications. This mostly stems from the lack of an extensive traffic sign dataset, standardized for benchmarking purposes. In light of the aforementioned, this paper presents a novel traffic sign dataset, which consists of the Carla Traffic Sign Detection (CTSD), and the Carla Traffic Sign Recognition Dataset (CATERED), targeting the detection and recognition processes respectively. Using the proposed dataset for training and evaluation, a deep Auto-Encoder algorithm is presented, demonstrating high accuracy in detecting and recognizing the distorted traffic signs. Finally, the system is further extended to a federated learning environment, exemplifying its applicability in modern decentralized and interconnected architectures. - BibTeXEndNoteKamal, Mohsin, Arnab Barua, Christian Vitale, Christos Laoudias, and George Ellinas. “GPS Location Spoofing Attack Detection for Enhancing the Security of Autonomous Vehicles”. IEEE 94th Vehicular Technology Conference 94th (September 2021).
@article{kamal2021location,
author = {Kamal, Mohsin and Barua, Arnab and Vitale, Christian and Laoudias, Christos and Ellinas, George},
journal = {IEEE 94th Vehicular Technology Conference},
keywords = {cybersecurity},
month = {September},
title = {GPS Location Spoofing Attack Detection for Enhancing the Security of Autonomous Vehicles},
volume = {94th},
year = 2021
}%0 Journal Article
%1 kamal2021location
%A Kamal, Mohsin
%A Barua, Arnab
%A Vitale, Christian
%A Laoudias, Christos
%A Ellinas, George
%D 2021
%J IEEE 94th Vehicular Technology Conference
%T GPS Location Spoofing Attack Detection for Enhancing the Security of Autonomous Vehicles
%V 94th - AbstractBibTeXEndNotePapandreou, Andreas, Andreas Kloukiniotis, Aris Lalos, and Konstantinos Moustakas. “Deep Multi-Modal Data Analysis and Fusion for Robust Scene Understanding in CAVs”. Edited by IEEE MMSP 2021 (October 2021).Deep learning (DL) tends to be the integral part of Autonomous Vehicles (AVs). Therefore the development of scene analysis modules that are robust to various vulnerabilities such as adversarial inputs or cyber-attacks is becoming an imperative need for the future AV perception systems. In this paper, we deal with this issue by exploring the recent progress in Artificial Intelligence (AI) and Machine Learning (ML) to provide holistic situational awareness and eliminate the effect of the previous attacks on the scene analysis modules. We propose novel multi-modal approaches against which achieve robustness to adversarial attacks, by appropriately modifying the analysis Neural networks and by utilizing late fusion methods. More specifically, we propose a holistic approach by adding new layers to a 2D segmentation DL model enhancing its robustness to adversarial noise. Then, a novel late fusion technique has been applied, by extracting direct features from the 3D space and project them into the 2D segmented space for identifying inconsistencies. Extensive evaluation studies using the KITTI odometry dataset provide promising performance results under various types of noise.
@article{papandreou2021multimodal,
abstract = {Deep learning (DL) tends to be the integral part of Autonomous Vehicles (AVs). Therefore the development of scene analysis modules that are robust to various vulnerabilities such as adversarial inputs or cyber-attacks is becoming an imperative need for the future AV perception systems. In this paper, we deal with this issue by exploring the recent progress in Artificial Intelligence (AI) and Machine Learning (ML) to provide holistic situational awareness and eliminate the effect of the previous attacks on the scene analysis modules. We propose novel multi-modal approaches against which achieve robustness to adversarial attacks, by appropriately modifying the analysis Neural networks and by utilizing late fusion methods. More specifically, we propose a holistic approach by adding new layers to a 2D segmentation DL model enhancing its robustness to adversarial noise. Then, a novel late fusion technique has been applied, by extracting direct features from the 3D space and project them into the 2D segmented space for identifying inconsistencies. Extensive evaluation studies using the KITTI odometry dataset provide promising performance results under various types of noise.},
author = {Papandreou, Andreas and Kloukiniotis, Andreas and Lalos, Aris and Moustakas, Konstantinos},
editor = {2021, IEEE MMSP},
keywords = {cybersecurity},
month = {October},
title = {Deep multi-modal data analysis and fusion for robust scene understanding in CAVs},
year = 2021
}%0 Journal Article
%1 papandreou2021multimodal
%A Papandreou, Andreas
%A Kloukiniotis, Andreas
%A Lalos, Aris
%A Moustakas, Konstantinos
%D 2021
%E 2021, IEEE MMSP
%T Deep multi-modal data analysis and fusion for robust scene understanding in CAVs
%X Deep learning (DL) tends to be the integral part of Autonomous Vehicles (AVs). Therefore the development of scene analysis modules that are robust to various vulnerabilities such as adversarial inputs or cyber-attacks is becoming an imperative need for the future AV perception systems. In this paper, we deal with this issue by exploring the recent progress in Artificial Intelligence (AI) and Machine Learning (ML) to provide holistic situational awareness and eliminate the effect of the previous attacks on the scene analysis modules. We propose novel multi-modal approaches against which achieve robustness to adversarial attacks, by appropriately modifying the analysis Neural networks and by utilizing late fusion methods. More specifically, we propose a holistic approach by adding new layers to a 2D segmentation DL model enhancing its robustness to adversarial noise. Then, a novel late fusion technique has been applied, by extracting direct features from the 3D space and project them into the 2D segmented space for identifying inconsistencies. Extensive evaluation studies using the KITTI odometry dataset provide promising performance results under various types of noise. - AbstractURLBibTeXEndNoteDOIVitale, Christian, Nikos Piperigkos, Christos Laoudias, Georgios Ellinas, Jordi Casademont, Josep Escrig, Andreas Kloukiniotis, Aris S. Lalos, Konstantinos Moustakas, Rodrigo Diaz Rodriguez, Daniel Baños, Gemma Roqueta Crusats, Petros Kapsalas, Klaus-Peter Hofmann, and Pouria Sayyad Khodashenas. “CARAMEL: Results on a Secure Architecture for Connected and Autonomous Vehicles Detecting GPS Spoofing Attacks”. In EURASIP Journal on Wireless Communications and Networking. Springer, 2021, Springer, 2021. doi:10.1186/s13638-021-01971-x.The main goal of the H2020-CARAMEL project is to address the cybersecurity gaps introduced by the new technological domains adopted by modern vehicles applying, among others, advanced Artificial Intelligence and Machine Learning techniques. As a result, CARAMEL enhances the protection against threats related to automated driving, smart charging of Electric Vehicles, and communication among vehicles or between vehicles and the roadside infrastructure. This work focuses on the latter and presents the CARAMEL architecture aiming at assessing the integrity of the information transmitted by vehicles, as well as at improving the security and privacy of communication for connected and autonomous driving. The proposed architecture includes: (1) multi-radio access technology capabilities, with simultaneous 802.11p and LTE-Uu support, enabled by the connectivity infrastructure; (2) a MEC platform, where, among others, algorithms for detecting attacks are implemented; (3) an intelligent On-Board Unit with anti-hacking features inside the vehicle; (4) a Public Key Infrastructure that validates in real-time the integrity of vehicle’s data transmissions. As an indicative application, the interaction between the entities of the CARAMEL architecture is showcased in case of a GPS spoofing attack scenario. Adopted attack detection techniques exploit robust in-vehicle and cooperative approaches that do not rely on encrypted GPS signals, but only on measurements available in the CARAMEL architecture.
@inproceedings{noauthororeditor2021caramel,
abstract = {The main goal of the H2020-CARAMEL project is to address the cybersecurity gaps introduced by the new technological domains adopted by modern vehicles applying, among others, advanced Artificial Intelligence and Machine Learning techniques. As a result, CARAMEL enhances the protection against threats related to automated driving, smart charging of Electric Vehicles, and communication among vehicles or between vehicles and the roadside infrastructure. This work focuses on the latter and presents the CARAMEL architecture aiming at assessing the integrity of the information transmitted by vehicles, as well as at improving the security and privacy of communication for connected and autonomous driving. The proposed architecture includes: (1) multi-radio access technology capabilities, with simultaneous 802.11p and LTE-Uu support, enabled by the connectivity infrastructure; (2) a MEC platform, where, among others, algorithms for detecting attacks are implemented; (3) an intelligent On-Board Unit with anti-hacking features inside the vehicle; (4) a Public Key Infrastructure that validates in real-time the integrity of vehicle’s data transmissions. As an indicative application, the interaction between the entities of the CARAMEL architecture is showcased in case of a GPS spoofing attack scenario. Adopted attack detection techniques exploit robust in-vehicle and cooperative approaches that do not rely on encrypted GPS signals, but only on measurements available in the CARAMEL architecture.},
author = {Vitale, Christian and Piperigkos, Nikos and Laoudias, Christos and Ellinas, Georgios and Casademont, Jordi and Escrig, Josep and Kloukiniotis, Andreas and Lalos, Aris S. and Moustakas, Konstantinos and Diaz Rodriguez, Rodrigo and Baños, Daniel and Roqueta Crusats, Gemma and Kapsalas, Petros and Hofmann, Klaus-Peter and Khodashenas, Pouria Sayyad},
booktitle = {EURASIP Journal on Wireless Communications and Networking},
keywords = {cybersecurity},
publisher = {Springer},
title = {CARAMEL: results on a secure architecture for connected and autonomous vehicles detecting GPS spoofing attacks},
year = 2021
}%0 Conference Paper
%1 noauthororeditor2021caramel
%A Vitale, Christian
%A Piperigkos, Nikos
%A Laoudias, Christos
%A Ellinas, Georgios
%A Casademont, Jordi
%A Escrig, Josep
%A Kloukiniotis, Andreas
%A Lalos, Aris S.
%A Moustakas, Konstantinos
%A Diaz Rodriguez, Rodrigo
%A Baños, Daniel
%A Roqueta Crusats, Gemma
%A Kapsalas, Petros
%A Hofmann, Klaus-Peter
%A Khodashenas, Pouria Sayyad
%B EURASIP Journal on Wireless Communications and Networking
%D 2021
%I Springer
%R 10.1186/s13638-021-01971-x
%T CARAMEL: results on a secure architecture for connected and autonomous vehicles detecting GPS spoofing attacks
%U https://doi.org/10.1186/s13638-021-01971-x
%X The main goal of the H2020-CARAMEL project is to address the cybersecurity gaps introduced by the new technological domains adopted by modern vehicles applying, among others, advanced Artificial Intelligence and Machine Learning techniques. As a result, CARAMEL enhances the protection against threats related to automated driving, smart charging of Electric Vehicles, and communication among vehicles or between vehicles and the roadside infrastructure. This work focuses on the latter and presents the CARAMEL architecture aiming at assessing the integrity of the information transmitted by vehicles, as well as at improving the security and privacy of communication for connected and autonomous driving. The proposed architecture includes: (1) multi-radio access technology capabilities, with simultaneous 802.11p and LTE-Uu support, enabled by the connectivity infrastructure; (2) a MEC platform, where, among others, algorithms for detecting attacks are implemented; (3) an intelligent On-Board Unit with anti-hacking features inside the vehicle; (4) a Public Key Infrastructure that validates in real-time the integrity of vehicle’s data transmissions. As an indicative application, the interaction between the entities of the CARAMEL architecture is showcased in case of a GPS spoofing attack scenario. Adopted attack detection techniques exploit robust in-vehicle and cooperative approaches that do not rely on encrypted GPS signals, but only on measurements available in the CARAMEL architecture. - URLBibTeXEndNoteDOIPapachristodoulou, A, Christos Kyrkou, and Theocharis Theocharides. “DriveGuard: Robustification of Automated Driving Systems With Spatio-Temporal Convolutional Autoencoder”. In Autonomous Vehicle Vision Workshop 2021. IEEE, 2021, IEEE, 2021. doi:10.1109/WACVW52041.2021.00016.
@inproceedings{Papachristodoulou_driveguard,
author = {Papachristodoulou, A and Kyrkou, Christos and Theocharides, Theocharis},
booktitle = {Autonomous Vehicle Vision Workshop 2021},
keywords = {cybersecurity},
note = {https://openaccess.thecvf.com/content/WACV2021W/AVV/papers/Papachristodoulou_DriveGuard_Robustification_of_Automated_Driving_Systems_With_Deep_Spatio-Temporal_Convolutional_WACVW_2021_paper.pdf},
publisher = {IEEE},
title = {DriveGuard: Robustification of Automated Driving Systems with Spatio-Temporal Convolutional Autoencoder},
year = 2021
}%0 Conference Paper
%1 Papachristodoulou_driveguard
%A Papachristodoulou, A
%A Kyrkou, Christos
%A Theocharides, Theocharis
%B Autonomous Vehicle Vision Workshop 2021
%D 2021
%I IEEE
%R 10.1109/WACVW52041.2021.00016
%T DriveGuard: Robustification of Automated Driving Systems with Spatio-Temporal Convolutional Autoencoder
%U https://ieeexplore.ieee.org/document/9407818
2020
- AbstractURLBibTeXEndNoteDOICasademont, J., B. Cordero, D. Camps-Mur, L. A. M. da Conceição, A. Lalos, C. Vitale, C. Laoudias, and P. S. Khodashenas. “Multi-Radio V2X Communications Interoperability Through a Multi-Access Edge Computing (MEC)”. In 2020 22nd International Conference on Transparent Optical Networks (ICTON), 1–4. doi:10.1109/ICTON51198.2020.9203495.Nowadays, we are ready to have precommercial Cooperative Intelligent Transport Systems (C-ITS), nevertheless there exist challenging functional and security aspects that need to be addressed. One of them is the fact that, in every era, there will be several radio technologies which will be used by vehicles that need to be connected between them, therefore, the systems needs to provide interoperability services. The other critical issue is to reinforce security against attacks on localization receivers or in vehicles equipment. Most of these functions are based in a large amount of computation power, to this end, this paper presents the approach taken by H2020 CARAMEL project, using a Multi-access Edge Computing (MEC) that could provide the necessary performance assets.
@inproceedings{9203495,
abstract = {Nowadays, we are ready to have precommercial Cooperative Intelligent Transport Systems (C-ITS), nevertheless there exist challenging functional and security aspects that need to be addressed. One of them is the fact that, in every era, there will be several radio technologies which will be used by vehicles that need to be connected between them, therefore, the systems needs to provide interoperability services. The other critical issue is to reinforce security against attacks on localization receivers or in vehicles equipment. Most of these functions are based in a large amount of computation power, to this end, this paper presents the approach taken by H2020 CARAMEL project, using a Multi-access Edge Computing (MEC) that could provide the necessary performance assets.},
author = {Casademont, J. and Cordero, B. and Camps-Mur, D. and da Conceição, L. A. M. and Lalos, A. and Vitale, C. and Laoudias, C. and Khodashenas, P. S.},
booktitle = {2020 22nd International Conference on Transparent Optical Networks (ICTON)},
keywords = {cybersecurity},
pages = {1-4},
title = {Multi-Radio V2X Communications Interoperability Through a Multi-Access Edge Computing (MEC)},
year = 2020
}%0 Conference Paper
%1 9203495
%A Casademont, J.
%A Cordero, B.
%A Camps-Mur, D.
%A da Conceição, L. A. M.
%A Lalos, A.
%A Vitale, C.
%A Laoudias, C.
%A Khodashenas, P. S.
%B 2020 22nd International Conference on Transparent Optical Networks (ICTON)
%D 2020
%P 1-4
%R 10.1109/ICTON51198.2020.9203495
%T Multi-Radio V2X Communications Interoperability Through a Multi-Access Edge Computing (MEC)
%U https://ieeexplore.ieee.org/abstract/document/9203495
%X Nowadays, we are ready to have precommercial Cooperative Intelligent Transport Systems (C-ITS), nevertheless there exist challenging functional and security aspects that need to be addressed. One of them is the fact that, in every era, there will be several radio technologies which will be used by vehicles that need to be connected between them, therefore, the systems needs to provide interoperability services. The other critical issue is to reinforce security against attacks on localization receivers or in vehicles equipment. Most of these functions are based in a large amount of computation power, to this end, this paper presents the approach taken by H2020 CARAMEL project, using a Multi-access Edge Computing (MEC) that could provide the necessary performance assets. - AbstractURLBibTeXEndNoteDOIVitale, C., N. Piperigkos, C. Laoudias, G. Ellinas, J. Casademont, P. Sayyad Khodashenas, A. Kloukiniotis, A. S. Lalos, K. Moustakas, P. Barrientos Lobato, J. Moreno Castillo, P. Kapsalas, and K. P. Hofmann. “The CARAMEL Project: A Secure Architecture for Connected and Autonomous Vehicles”. In 2020 European Conference on Networks and Communications (EuCNC), 133–138. doi:10.1109/EuCNC48522.2020.9200945.Connected and Autonomous Vehicles (CAVs) rely on Global Navigation Satellite Systems (GNSS), e.g., the Global Positioning System (GPS), for the provision of accurate location information for various functionalities including Vehicle-to-Vehicle/Infrastructure (V2V/V2I) communication and self-navigation. However, GNSS-based location awareness is prone to spoofing attacks, where the attacker generates counterfeit satellite signals. This in turn poses a serious threat to the CAV, e.g., car, drone, etc., as well as the surrounding entities. Thus, this threat needs to be detected reliably and mitigated timely to prevent undesired consequences (e.g., damages, casualties, etc.). To this end, this work proposes a location verification solution that leverages in-vehicle sensor readings (e.g., accelerometer, etc.) and Signals of Opportunity (SoO), as an alternative source of location information. In particular, the multimodal sensor data with SoO location measurements are fused by means of a Kalman filter and the estimated fusion-based location is used to verify the location output of the GPS receiver. In case the GPS location deviates considerably from the fusion-based location, then a location spoofing attack is ascertained. Preliminary experimental results with real GPS and sensor data collected with a drone demonstrate the effectiveness of the proposed approach.
@inproceedings{9200945,
abstract = {Connected and Autonomous Vehicles (CAVs) rely on Global Navigation Satellite Systems (GNSS), e.g., the Global Positioning System (GPS), for the provision of accurate location information for various functionalities including Vehicle-to-Vehicle/Infrastructure (V2V/V2I) communication and self-navigation. However, GNSS-based location awareness is prone to spoofing attacks, where the attacker generates counterfeit satellite signals. This in turn poses a serious threat to the CAV, e.g., car, drone, etc., as well as the surrounding entities. Thus, this threat needs to be detected reliably and mitigated timely to prevent undesired consequences (e.g., damages, casualties, etc.). To this end, this work proposes a location verification solution that leverages in-vehicle sensor readings (e.g., accelerometer, etc.) and Signals of Opportunity (SoO), as an alternative source of location information. In particular, the multimodal sensor data with SoO location measurements are fused by means of a Kalman filter and the estimated fusion-based location is used to verify the location output of the GPS receiver. In case the GPS location deviates considerably from the fusion-based location, then a location spoofing attack is ascertained. Preliminary experimental results with real GPS and sensor data collected with a drone demonstrate the effectiveness of the proposed approach.},
author = {Vitale, C. and Piperigkos, N. and Laoudias, C. and Ellinas, G. and Casademont, J. and Sayyad Khodashenas, P. and Kloukiniotis, A. and Lalos, A. S. and Moustakas, K. and Barrientos Lobato, P. and Moreno Castillo, J. and Kapsalas, P. and Hofmann, K. P.},
booktitle = {2020 European Conference on Networks and Communications (EuCNC)},
keywords = {cybersecurity},
pages = {133-138},
title = {The CARAMEL Project: a Secure Architecture for Connected and Autonomous Vehicles},
year = 2020
}%0 Conference Paper
%1 9200945
%A Vitale, C.
%A Piperigkos, N.
%A Laoudias, C.
%A Ellinas, G.
%A Casademont, J.
%A Sayyad Khodashenas, P.
%A Kloukiniotis, A.
%A Lalos, A. S.
%A Moustakas, K.
%A Barrientos Lobato, P.
%A Moreno Castillo, J.
%A Kapsalas, P.
%A Hofmann, K. P.
%B 2020 European Conference on Networks and Communications (EuCNC)
%D 2020
%P 133-138
%R 10.1109/EuCNC48522.2020.9200945
%T The CARAMEL Project: a Secure Architecture for Connected and Autonomous Vehicles
%U https://ieeexplore.ieee.org/document/9200945
%X Connected and Autonomous Vehicles (CAVs) rely on Global Navigation Satellite Systems (GNSS), e.g., the Global Positioning System (GPS), for the provision of accurate location information for various functionalities including Vehicle-to-Vehicle/Infrastructure (V2V/V2I) communication and self-navigation. However, GNSS-based location awareness is prone to spoofing attacks, where the attacker generates counterfeit satellite signals. This in turn poses a serious threat to the CAV, e.g., car, drone, etc., as well as the surrounding entities. Thus, this threat needs to be detected reliably and mitigated timely to prevent undesired consequences (e.g., damages, casualties, etc.). To this end, this work proposes a location verification solution that leverages in-vehicle sensor readings (e.g., accelerometer, etc.) and Signals of Opportunity (SoO), as an alternative source of location information. In particular, the multimodal sensor data with SoO location measurements are fused by means of a Kalman filter and the estimated fusion-based location is used to verify the location output of the GPS receiver. In case the GPS location deviates considerably from the fusion-based location, then a location spoofing attack is ascertained. Preliminary experimental results with real GPS and sensor data collected with a drone demonstrate the effectiveness of the proposed approach. - AbstractBibTeXEndNoteDOIPiperigkos, N., A. S. Lalos, K. Berberidis, C. Laoudias, and K. Moustakas. “5G Enabled Cooperative Localization of Connected and Semi-Autonomous Vehicles via Sparse Laplacian Processing”. In 2020 22nd International Conference on Transparent Optical Networks (ICTON), 1–4. doi:10.1109/ICTON51198.2020.9203314.Cooperative Localization has received extensive interest from several scientific communities including Robotics, Optimization, Signal Processing and Wireless Communications. It is expected to become a major aspect for a number of crucial applications in the field of Connected and (Semi-) Autonomous vehicles (CAVs), such as collision avoidance/warning, cooperative adaptive cruise control, safely navigation, etc. 5G mobile networks will be the key to providing connectivity for vehicle to everything (V2X) communications, allowing CAVs to share with other entities of the network the data they collect and measure. Typical measurement models usually deployed for this problem, are absolute position information from Global Positioning System (GPS), relative distance to neighbouring vehicles and relative angle or azimuth angle, from Light Detection and Ranging (LIDAR) or Radio Detection and Ranging (RADAR) sensors. In this paper, we provide a cooperative estimation approach that performs multi modal-fusion between interconnected vehicles. This method is based on a Graph Signal Processing tool, known as Laplacian Graph Processing, and significantly outperforms existing method both in terms of attained accuracy and computational complexity.
@inproceedings{9203314,
abstract = {Cooperative Localization has received extensive interest from several scientific communities including Robotics, Optimization, Signal Processing and Wireless Communications. It is expected to become a major aspect for a number of crucial applications in the field of Connected and (Semi-) Autonomous vehicles (CAVs), such as collision avoidance/warning, cooperative adaptive cruise control, safely navigation, etc. 5G mobile networks will be the key to providing connectivity for vehicle to everything (V2X) communications, allowing CAVs to share with other entities of the network the data they collect and measure. Typical measurement models usually deployed for this problem, are absolute position information from Global Positioning System (GPS), relative distance to neighbouring vehicles and relative angle or azimuth angle, from Light Detection and Ranging (LIDAR) or Radio Detection and Ranging (RADAR) sensors. In this paper, we provide a cooperative estimation approach that performs multi modal-fusion between interconnected vehicles. This method is based on a Graph Signal Processing tool, known as Laplacian Graph Processing, and significantly outperforms existing method both in terms of attained accuracy and computational complexity.},
author = {Piperigkos, N. and Lalos, A. S. and Berberidis, K. and Laoudias, C. and Moustakas, K.},
booktitle = {2020 22nd International Conference on Transparent Optical Networks (ICTON)},
keywords = {cybersecurity},
pages = {1-4},
title = {5G Enabled Cooperative Localization of Connected and Semi-Autonomous Vehicles via Sparse Laplacian Processing},
year = 2020
}%0 Conference Paper
%1 9203314
%A Piperigkos, N.
%A Lalos, A. S.
%A Berberidis, K.
%A Laoudias, C.
%A Moustakas, K.
%B 2020 22nd International Conference on Transparent Optical Networks (ICTON)
%D 2020
%P 1-4
%R 10.1109/ICTON51198.2020.9203314
%T 5G Enabled Cooperative Localization of Connected and Semi-Autonomous Vehicles via Sparse Laplacian Processing
%X Cooperative Localization has received extensive interest from several scientific communities including Robotics, Optimization, Signal Processing and Wireless Communications. It is expected to become a major aspect for a number of crucial applications in the field of Connected and (Semi-) Autonomous vehicles (CAVs), such as collision avoidance/warning, cooperative adaptive cruise control, safely navigation, etc. 5G mobile networks will be the key to providing connectivity for vehicle to everything (V2X) communications, allowing CAVs to share with other entities of the network the data they collect and measure. Typical measurement models usually deployed for this problem, are absolute position information from Global Positioning System (GPS), relative distance to neighbouring vehicles and relative angle or azimuth angle, from Light Detection and Ranging (LIDAR) or Radio Detection and Ranging (RADAR) sensors. In this paper, we provide a cooperative estimation approach that performs multi modal-fusion between interconnected vehicles. This method is based on a Graph Signal Processing tool, known as Laplacian Graph Processing, and significantly outperforms existing method both in terms of attained accuracy and computational complexity. - URLBibTeXEndNoteDOIArgyropoulos, Nikolaos, Pouria Sayyad Khodashenas, Orestis Mavropoulosa, Eirini Karapistoli, Anastasios Lytos, Paris Alexandros Karypidis, and Peter Hofmann Klaus. “Addressing Cybersecurity in the Next Generation Mobility Ecosystem With CARAMEL”. In. 23rd EURO Working Group on Transportation Meeting, EWGT 2020, 16-18 September 2020,Paphos, Cyprus, 2020, 23rd EURO Working Group on Transportation Meeting, EWGT 2020, 16-18 September 2020,Paphos, Cyprus, 2020. doi:10.1016/j.trpro.2021.01.036.
@conference{Argyropoulos2020Addressing,
author = {Argyropoulos, Nikolaos and Sayyad Khodashenas, Pouria and Mavropoulosa, Orestis and Karapistoli, Eirini and Lytos, Anastasios and Karypidis, Paris Alexandros and Klaus, Peter Hofmann},
keywords = {cybersecurity},
publisher = {23rd EURO Working Group on Transportation Meeting, EWGT 2020, 16-18 September 2020,Paphos, Cyprus},
title = {Addressing Cybersecurity in the Next Generation Mobility Ecosystem with CARAMEL},
year = 2020
}%0 Generic
%1 Argyropoulos2020Addressing
%A Argyropoulos, Nikolaos
%A Sayyad Khodashenas, Pouria
%A Mavropoulosa, Orestis
%A Karapistoli, Eirini
%A Lytos, Anastasios
%A Karypidis, Paris Alexandros
%A Klaus, Peter Hofmann
%D 2020
%I 23rd EURO Working Group on Transportation Meeting, EWGT 2020, 16-18 September 2020,Paphos, Cyprus
%R 10.1016/j.trpro.2021.01.036
%T Addressing Cybersecurity in the Next Generation Mobility Ecosystem with CARAMEL
%U https://www.sciencedirect.com/science/article/pii/S2352146521000685 - AbstractURLBibTeXEndNoteDOISouli, N., C. Laoudias, P. Kolios, C. Vitale, G. Ellinas, A. Lalos, J. Casademont, P. S. Khodashenas, and P. Kapsalas. “GNSS Location Verification in Connected and Autonomous Vehicles Using in-Vehicle Multimodal Sensor Data Fusion”. In 2020 22nd International Conference on Transparent Optical Networks (ICTON), 1–4. doi:10.1109/ICTON51198.2020.9203087.Connected and Autonomous Vehicles (CAVs) rely on Global Navigation Satellite Systems (GNSS), e.g., the Global Positioning System (GPS), for the provision of accurate location information for various functionalities including Vehicle-to-Vehicle/Infrastructure (V2V/V2I) communication and self-navigation. However, GNSS-based location awareness is prone to spoofing attacks, where the attacker generates counterfeit satellite signals. This in turn poses a serious threat to the CAV, e.g., car, drone, etc., as well as the surrounding entities. Thus, this threat needs to be detected reliably and mitigated timely to prevent undesired consequences (e.g., damages, casualties, etc.). To this end, this work proposes a location verification solution that leverages in-vehicle sensor readings (e.g., accelerometer, etc.) and Signals of Opportunity (SoO), as an alternative source of location information. In particular, the multimodal sensor data with SoO location measurements are fused by means of a Kalman filter and the estimated fusion-based location is used to verify the location output of the GPS receiver. In case the GPS location deviates considerably from the fusion-based location, then a location spoofing attack is ascertained. Preliminary experimental results with real GPS and sensor data collected with a drone demonstrate the effectiveness of the proposed approach.
@inproceedings{9203087,
abstract = {Connected and Autonomous Vehicles (CAVs) rely on Global Navigation Satellite Systems (GNSS), e.g., the Global Positioning System (GPS), for the provision of accurate location information for various functionalities including Vehicle-to-Vehicle/Infrastructure (V2V/V2I) communication and self-navigation. However, GNSS-based location awareness is prone to spoofing attacks, where the attacker generates counterfeit satellite signals. This in turn poses a serious threat to the CAV, e.g., car, drone, etc., as well as the surrounding entities. Thus, this threat needs to be detected reliably and mitigated timely to prevent undesired consequences (e.g., damages, casualties, etc.). To this end, this work proposes a location verification solution that leverages in-vehicle sensor readings (e.g., accelerometer, etc.) and Signals of Opportunity (SoO), as an alternative source of location information. In particular, the multimodal sensor data with SoO location measurements are fused by means of a Kalman filter and the estimated fusion-based location is used to verify the location output of the GPS receiver. In case the GPS location deviates considerably from the fusion-based location, then a location spoofing attack is ascertained. Preliminary experimental results with real GPS and sensor data collected with a drone demonstrate the effectiveness of the proposed approach.},
author = {Souli, N. and Laoudias, C. and Kolios, P. and Vitale, C. and Ellinas, G. and Lalos, A. and Casademont, J. and Khodashenas, P. S. and Kapsalas, P.},
booktitle = {2020 22nd International Conference on Transparent Optical Networks (ICTON)},
keywords = {cybersecurity},
pages = {1-4},
title = {GNSS Location Verification in Connected and Autonomous Vehicles Using in-Vehicle Multimodal Sensor Data Fusion},
year = 2020
}%0 Conference Paper
%1 9203087
%A Souli, N.
%A Laoudias, C.
%A Kolios, P.
%A Vitale, C.
%A Ellinas, G.
%A Lalos, A.
%A Casademont, J.
%A Khodashenas, P. S.
%A Kapsalas, P.
%B 2020 22nd International Conference on Transparent Optical Networks (ICTON)
%D 2020
%P 1-4
%R 10.1109/ICTON51198.2020.9203087
%T GNSS Location Verification in Connected and Autonomous Vehicles Using in-Vehicle Multimodal Sensor Data Fusion
%U https://ieeexplore.ieee.org/abstract/document/9203087
%X Connected and Autonomous Vehicles (CAVs) rely on Global Navigation Satellite Systems (GNSS), e.g., the Global Positioning System (GPS), for the provision of accurate location information for various functionalities including Vehicle-to-Vehicle/Infrastructure (V2V/V2I) communication and self-navigation. However, GNSS-based location awareness is prone to spoofing attacks, where the attacker generates counterfeit satellite signals. This in turn poses a serious threat to the CAV, e.g., car, drone, etc., as well as the surrounding entities. Thus, this threat needs to be detected reliably and mitigated timely to prevent undesired consequences (e.g., damages, casualties, etc.). To this end, this work proposes a location verification solution that leverages in-vehicle sensor readings (e.g., accelerometer, etc.) and Signals of Opportunity (SoO), as an alternative source of location information. In particular, the multimodal sensor data with SoO location measurements are fused by means of a Kalman filter and the estimated fusion-based location is used to verify the location output of the GPS receiver. In case the GPS location deviates considerably from the fusion-based location, then a location spoofing attack is ascertained. Preliminary experimental results with real GPS and sensor data collected with a drone demonstrate the effectiveness of the proposed approach. - AbstractURLBibTeXEndNoteDOIKantartopoulos, Panagiotis, Nikolaos Pitropakis, Alexios Mylonas, and Nicolas Kylilis. “Exploring Adversarial Attacks and Defences for Fake Twitter Account Detection”. Technologies 8, no. 4 (2020): 64. doi:https://doi.org/10.3390/technologies8040064.Social media has become very popular and important in people’s lives, as personal ideas, beliefs and opinions are expressed and shared through them. Unfortunately, social networks, and specifically Twitter, suffer from massive existence and perpetual creation of fake users. Their goal is to deceive other users employing various methods, or even create a stream of fake news and opinions in order to influence an idea upon a specific subject, thus impairing the platform’s integrity. As such, machine learning techniques have been widely used in social networks to address this type of threat by automatically identifying fake accounts. Nonetheless, threat actors update their arsenal and launch a range of sophisticated attacks to undermine this detection procedure, either during the training or test phase, rendering machine learning algorithms vulnerable to adversarial attacks. Our work examines the propagation of adversarial attacks in machine learning based detection for fake Twitter accounts, which is based on AdaBoost. Moreover, we propose and evaluate the use of k-NN as a countermeasure to remedy the effects of the adversarial attacks that we have implemented.
@article{kylilis2020exploring,
abstract = {Social media has become very popular and important in people’s lives, as personal ideas, beliefs and opinions are expressed and shared through them. Unfortunately, social networks, and specifically Twitter, suffer from massive existence and perpetual creation of fake users. Their goal is to deceive other users employing various methods, or even create a stream of fake news and opinions in order to influence an idea upon a specific subject, thus impairing the platform’s integrity. As such, machine learning techniques have been widely used in social networks to address this type of threat by automatically identifying fake accounts. Nonetheless, threat actors update their arsenal and launch a range of sophisticated attacks to undermine this detection procedure, either during the training or test phase, rendering machine learning algorithms vulnerable to adversarial attacks. Our work examines the propagation of adversarial attacks in machine learning based detection for fake Twitter accounts, which is based on AdaBoost. Moreover, we propose and evaluate the use of k-NN as a countermeasure to remedy the effects of the adversarial attacks that we have implemented.},
author = {Kantartopoulos, Panagiotis and Pitropakis, Nikolaos and Mylonas, Alexios and Kylilis, Nicolas},
journal = {Technologies},
keywords = {cybersecurity},
number = 4,
pages = 64,
publisher = {Multidisciplinary Digital Publishing Institute},
title = {Exploring Adversarial Attacks and Defences for Fake Twitter Account Detection},
volume = 8,
year = 2020
}%0 Journal Article
%1 kylilis2020exploring
%A Kantartopoulos, Panagiotis
%A Pitropakis, Nikolaos
%A Mylonas, Alexios
%A Kylilis, Nicolas
%D 2020
%I Multidisciplinary Digital Publishing Institute
%J Technologies
%N 4
%P 64
%R https://doi.org/10.3390/technologies8040064
%T Exploring Adversarial Attacks and Defences for Fake Twitter Account Detection
%U https://www.mdpi.com/2227-7080/8/4/64
%V 8
%X Social media has become very popular and important in people’s lives, as personal ideas, beliefs and opinions are expressed and shared through them. Unfortunately, social networks, and specifically Twitter, suffer from massive existence and perpetual creation of fake users. Their goal is to deceive other users employing various methods, or even create a stream of fake news and opinions in order to influence an idea upon a specific subject, thus impairing the platform’s integrity. As such, machine learning techniques have been widely used in social networks to address this type of threat by automatically identifying fake accounts. Nonetheless, threat actors update their arsenal and launch a range of sophisticated attacks to undermine this detection procedure, either during the training or test phase, rendering machine learning algorithms vulnerable to adversarial attacks. Our work examines the propagation of adversarial attacks in machine learning based detection for fake Twitter accounts, which is based on AdaBoost. Moreover, we propose and evaluate the use of k-NN as a countermeasure to remedy the effects of the adversarial attacks that we have implemented. - AbstractURLBibTeXEndNoteDOIPiperigkos, Nikos, and Aris S Lalos. “Impact of False Data Injection Attacks on Decentralized Electric Vehicle Charging Protocols”. In. 23rd EURO Working Group on Transportation Meeting, EWGT 2020, 16-18 September 2020,Paphos, Cyprus, 2020, 23rd EURO Working Group on Transportation Meeting, EWGT 2020, 16-18 September 2020,Paphos, Cyprus, 2020. doi:10.1016/j.trpro.2021.01.039.Electric vehicles (EVs) gain great attention nowadays since the electrification of private and public transport has a great potential to reduce greenhouse gas emissions and mitigate oil dependency. However, the influx of a large number of electrical loads without any coordination could have adverse affects to the electrical grid. More importantly, the complexity in the coordination of a large number of EVs, pose critical challenges in ensuring overall system integrity. A typical attack found in the controllers of connected EVs is false data injection (FDI), which can be utilized to distort real energy demand and supply figures. Energy distribution requests may therefore be erroneous. The lack of a proper coordination scheme, robust to such cyber attacks could cause voltage magnitude drops and unacceptable load peaks. In this work, we study the impact of FDI attacks, on various decentralized charging protocol with reduced computational requirements. The proposed decentralized EV charging algorithms only require from each EV to solve a local problem, hence the proposed implementation require low computational resources. An extensive evaluation study highlights the strengths and weaknesses of the presented solutions which are based on iterative convex optimization solvers .
@conference{piperigkos2020impact,
abstract = {Electric vehicles (EVs) gain great attention nowadays since the electrification of private and public transport has a great potential to reduce greenhouse gas emissions and mitigate oil dependency. However, the influx of a large number of electrical loads without any coordination could have adverse affects to the electrical grid. More importantly, the complexity in the coordination of a large number of EVs, pose critical challenges in ensuring overall system integrity. A typical attack found in the controllers of connected EVs is false data injection (FDI), which can be utilized to distort real energy demand and supply figures. Energy distribution requests may therefore be erroneous. The lack of a proper coordination scheme, robust to such cyber attacks could cause voltage magnitude drops and unacceptable load peaks. In this work, we study the impact of FDI attacks, on various decentralized charging protocol with reduced computational requirements. The proposed decentralized EV charging algorithms only require from each EV to solve a local problem, hence the proposed implementation require low computational resources. An extensive evaluation study highlights the strengths and weaknesses of the presented solutions which are based on iterative convex optimization solvers .},
author = {Piperigkos, Nikos and Lalos, Aris S},
keywords = {cybersecurity},
publisher = {23rd EURO Working Group on Transportation Meeting, EWGT 2020, 16-18 September 2020,Paphos, Cyprus},
title = {Impact of false data injection attacks on decentralized electric vehicle charging protocols},
year = 2020
}%0 Generic
%1 piperigkos2020impact
%A Piperigkos, Nikos
%A Lalos, Aris S
%D 2020
%I 23rd EURO Working Group on Transportation Meeting, EWGT 2020, 16-18 September 2020,Paphos, Cyprus
%R 10.1016/j.trpro.2021.01.039
%T Impact of false data injection attacks on decentralized electric vehicle charging protocols
%U https://www.sciencedirect.com/science/article/pii/S2352146521000715?via%3Dihub
%X Electric vehicles (EVs) gain great attention nowadays since the electrification of private and public transport has a great potential to reduce greenhouse gas emissions and mitigate oil dependency. However, the influx of a large number of electrical loads without any coordination could have adverse affects to the electrical grid. More importantly, the complexity in the coordination of a large number of EVs, pose critical challenges in ensuring overall system integrity. A typical attack found in the controllers of connected EVs is false data injection (FDI), which can be utilized to distort real energy demand and supply figures. Energy distribution requests may therefore be erroneous. The lack of a proper coordination scheme, robust to such cyber attacks could cause voltage magnitude drops and unacceptable load peaks. In this work, we study the impact of FDI attacks, on various decentralized charging protocol with reduced computational requirements. The proposed decentralized EV charging algorithms only require from each EV to solve a local problem, hence the proposed implementation require low computational resources. An extensive evaluation study highlights the strengths and weaknesses of the presented solutions which are based on iterative convex optimization solvers . - URLBibTeXEndNoteDOIKhadka, A, G. Efstathopoulos, P Karypidis, and A Lytos. “A Benchmarking Framework for Cyber-Attacks on Autonomous Vehicles”. In. 23rd EURO Working Group on Transportation Meeting, EWGT 2020, 16-18 September 2020,Paphos, Cyprus, 2020, 23rd EURO Working Group on Transportation Meeting, EWGT 2020, 16-18 September 2020,Paphos, Cyprus, 2020. doi:10.1016/j.trpro.2021.01.038.
@conference{Khadka2020Benchmarking,
author = {Khadka, A and Efstathopoulos, G. and Karypidis, P and Lytos, A},
keywords = {cybersecurity},
publisher = {23rd EURO Working Group on Transportation Meeting, EWGT 2020, 16-18 September 2020,Paphos, Cyprus},
title = {A benchmarking framework for cyber-attacks on autonomous vehicles},
year = 2020
}%0 Generic
%1 Khadka2020Benchmarking
%A Khadka, A
%A Efstathopoulos, G.
%A Karypidis, P
%A Lytos, A
%D 2020
%I 23rd EURO Working Group on Transportation Meeting, EWGT 2020, 16-18 September 2020,Paphos, Cyprus
%R 10.1016/j.trpro.2021.01.038
%T A benchmarking framework for cyber-attacks on autonomous vehicles
%U https://www.sciencedirect.com/science/article/pii/S2352146521000703 - AbstractURLBibTeXEndNoteDOIKyrkou, Christos, Andreas Papachristodoulou, Andreas Kloukiniotis, Andreas Papandreou, Aris S. Lalos, Konstantinos Moustakas, and Theocharis Theocharides. “Towards Artificial-Intelligence-Based Cybersecurity for Robustifying Automated Driving Systems Against Camera Sensor Attacks”. In 2020 IEEE Computer Society Annual Symposium on VLSI (ISVLSI), 476–481. doi:10.1109/ISVLSI49217.2020.00-11.CARAMEL is a European project that aims amongst others to improve and extend cyberthreat detection and mitigation techniques for automotive driving systems. This paper highlights the important role that advanced artificial intelligence and machine learning techniques can have in proactively addressing modern autonomous vehicle cybersecurity challenges and on mitigating associated safety risks when dealing with targetted attacks on a vehicle's camera sensors. The cybersecurity solutions developed by CARAMEL are based on powerful AI tools and algorithms to combat security risks in automated driving systems and will be hosted on embedded processors and platforms. As such, it will be possible to have a specialized anti-hacking device that addresses newly introduced technological dimensions for increased robustness and cybersecurity in addition to industry needs for high speed, low latency, functional safety, light weight, low power consumption.
@inproceedings{9154906,
abstract = {CARAMEL is a European project that aims amongst others to improve and extend cyberthreat detection and mitigation techniques for automotive driving systems. This paper highlights the important role that advanced artificial intelligence and machine learning techniques can have in proactively addressing modern autonomous vehicle cybersecurity challenges and on mitigating associated safety risks when dealing with targetted attacks on a vehicle's camera sensors. The cybersecurity solutions developed by CARAMEL are based on powerful AI tools and algorithms to combat security risks in automated driving systems and will be hosted on embedded processors and platforms. As such, it will be possible to have a specialized anti-hacking device that addresses newly introduced technological dimensions for increased robustness and cybersecurity in addition to industry needs for high speed, low latency, functional safety, light weight, low power consumption.},
author = {Kyrkou, Christos and Papachristodoulou, Andreas and Kloukiniotis, Andreas and Papandreou, Andreas and Lalos, Aris S. and Moustakas, Konstantinos and Theocharides, Theocharis},
booktitle = {2020 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)},
keywords = {cybersecurity},
month = {July},
pages = {476-481},
title = {Towards Artificial-Intelligence-Based Cybersecurity for Robustifying Automated Driving Systems Against Camera Sensor Attacks},
year = 2020
}%0 Conference Paper
%1 9154906
%A Kyrkou, Christos
%A Papachristodoulou, Andreas
%A Kloukiniotis, Andreas
%A Papandreou, Andreas
%A Lalos, Aris S.
%A Moustakas, Konstantinos
%A Theocharides, Theocharis
%B 2020 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)
%D 2020
%P 476-481
%R 10.1109/ISVLSI49217.2020.00-11
%T Towards Artificial-Intelligence-Based Cybersecurity for Robustifying Automated Driving Systems Against Camera Sensor Attacks
%U https://ieeexplore.ieee.org/document/9154906/
%X CARAMEL is a European project that aims amongst others to improve and extend cyberthreat detection and mitigation techniques for automotive driving systems. This paper highlights the important role that advanced artificial intelligence and machine learning techniques can have in proactively addressing modern autonomous vehicle cybersecurity challenges and on mitigating associated safety risks when dealing with targetted attacks on a vehicle's camera sensors. The cybersecurity solutions developed by CARAMEL are based on powerful AI tools and algorithms to combat security risks in automated driving systems and will be hosted on embedded processors and platforms. As such, it will be possible to have a specialized anti-hacking device that addresses newly introduced technological dimensions for increased robustness and cybersecurity in addition to industry needs for high speed, low latency, functional safety, light weight, low power consumption.