RX-ADS: Interpretable Anomaly Detection Using Adversarial ML for Electric Vehicle CAN Data

Wickramasinghe, Chathurika S.; Marino, Daniel L.; Mavikumbure, Harindra S.; Cobilean, Victor; Pennington, Timothy David; Varghese, Benny J.; Rieger, Craig G.; Manic, Milos

doi:10.1109/tits.2023.3294349

RX-ADS: Interpretable Anomaly Detection Using Adversarial ML for Electric Vehicle CAN Data

Journal Article · Mon Jul 24 00:00:00 EDT 2023 · IEEE Transactions on Intelligent Transportation Systems

DOI:https://doi.org/10.1109/tits.2023.3294349· OSTI ID:1999771

^[1]; ^[1]; ^[1]; ^[1]; Pennington, Timothy David ^[2]; Varghese, Benny J. ^[2]; ^[2]; ^[1]

Virginia Commonwealth University, Richmond, VA (United States)
Idaho National Laboratory (INL), Idaho Falls, ID (United States)

Recent year has brought considerable advancements in Electric Vehicles (EVs) and associated infrastructures/ communications. Intrusion Detection Systems (IDS) are widely deployed for anomaly detection in such critical infrastructures. This paper presents an Interpretable Anomaly Detection System (RX-ADS) for intrusion detection in CAN protocol communication in EVs. Contributions include: 1) window based feature extraction method; 2) deep Autoencoder based anomaly detection method; and 3) adversarial machine learning based explanation generation methodology. The presented approach was tested on two benchmark CAN datasets: OTIDS and Car Hacking. The anomaly detection performance of RX-ADS was compared against the state-of-the-art approaches on these datasets: HIDS and GIDS. The RX-ADS approach presented performance comparable to the HIDS approach (OTIDS dataset) and has outperformed HIDS and GIDS approaches (Car Hacking dataset). Further, the proposed approach was able to generate explanations for detected abnormal behaviors arising from various intrusions. Furthermore, these explanations were later validated by information used by domain experts to detect anomalies. Other advantages of RX-ADS include: 1) the method can be trained on unlabeled data; 2) explanations help experts in understanding anomalies and root course analysis, and also help with AI model debugging and diagnostics, ultimately improving user trust in AI systems.

View Accepted Manuscript (DOE)

Research Organization:: Idaho National Laboratory (INL), Idaho Falls, ID (United States)

Sponsoring Organization:: USDOE

Grant/Contract Number:: AC07-05ID14517

OSTI ID:: 1999771

Report Number(s):: INL/JOU--22-67678-Rev000

Journal Information:: IEEE Transactions on Intelligent Transportation Systems, Journal Name: IEEE Transactions on Intelligent Transportation Systems Journal Issue: 12 Vol. 24; ISSN 1524-9050

Publisher:: IEEECopyright Statement

Country of Publication:: United States

Language:: English

References (33)

Comparative Study of Machine Learning Methods for In-Vehicle Intrusion Detection Berger, Ivo; Rieke, Roland; Kolomeets, Maxim Computer Security https://doi.org/10.1007/978-3-030-12786-2_6	book	January 2019
An intrusion detection system for connected vehicles in smart cities Aloqaily, Moayad; Otoum, Safa; Ridhawi, Ismaeel Al Ad Hoc Networks, Vol. 90 https://doi.org/10.1016/j.adhoc.2019.02.001	journal	July 2019
Supervised Machine Learning: A Brief Primer Jiang, Tammy; Gradus, Jaimie L.; Rosellini, Anthony J. Behavior Therapy, Vol. 51, Issue 5 https://doi.org/10.1016/j.beth.2020.05.002	journal	September 2020
Distributed power generation planning for distribution networks using electric vehicles: Systematic attention to challenges and opportunities Singh, Bindeshwar; Dubey, Pankaj Kumar Journal of Energy Storage, Vol. 48 https://doi.org/10.1016/j.est.2022.104030	journal	April 2022
A novel hybrid intrusion detection method integrating anomaly detection with misuse detection Kim, Gisung; Lee, Seungmin; Kim, Sehun Expert Systems with Applications, Vol. 41, Issue 4 https://doi.org/10.1016/j.eswa.2013.08.066	journal	March 2014
Wild patterns: Ten years after the rise of adversarial machine learning Biggio, Battista; Roli, Fabio Pattern Recognition, Vol. 84 https://doi.org/10.1016/j.patcog.2018.07.023	journal	December 2018
CANet: An Unsupervised Intrusion Detection System for High Dimensional CAN Bus Data Hanselmann, Markus; Strauss, Thilo; Dormann, Katharina IEEE Access, Vol. 8 https://doi.org/10.1109/ACCESS.2020.2982544	journal	January 2020
ResNet Autoencoders for Unsupervised Feature Learning From High-Dimensional Data: Deep Models Resistant to Performance Degradation Wickramasinghe, Chathurika S.; Marino, Daniel L.; Manic, Milos IEEE Access, Vol. 9 https://doi.org/10.1109/ACCESS.2021.3064819	journal	January 2021
Explainable Unsupervised Machine Learning for Cyber-Physical Systems Wickramasinghe, Chathurika S.; Amarasinghe, Kasun; Marino, Daniel L. IEEE Access, Vol. 9 https://doi.org/10.1109/ACCESS.2021.3112397	journal	January 2021
Anomaly Detection in Automobile Control Network Data with Long Short-Term Memory Networks Taylor, Adrian; Leblanc, Sylvain; Japkowicz, Nathalie 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA) https://doi.org/10.1109/DSAA.2016.20	conference	October 2016
Detection of Automotive CAN Cyber-Attacks by Identifying Packet Timing Anomalies in Time Windows Tomlinson, Andrew; Bryans, Jeremy; Shaikh, Siraj Ahmed 2018 48th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W) https://doi.org/10.1109/DSN-W.2018.00069	conference	June 2018
An Effective In-Vehicle CAN Bus Intrusion Detection System Using CNN Deep Learning Approach Delwar Hossain, Md; Inoue, Hiroyuki; Ochiai, Hideya GLOBECOM 2020 - 2020 IEEE Global Communications Conference https://doi.org/10.1109/GLOBECOM42002.2020.9322395	conference	December 2020
Trustworthy AI Development Guidelines for Human System Interaction Wickramasinghe, Chathurika S.; Marino, Daniel L.; Grandio, Javier 2020 13th International Conference on Human System Interaction (HSI) https://doi.org/10.1109/HSI49210.2020.9142644	conference	June 2020
Recent Advancements and Developments for Electric Vehicle Technology Zakaria, Haji; Hamid, Mounir; Abdellatif, El Marjani 2019 International Conference of Computer Science and Renewable Energies (ICCSRE) https://doi.org/10.1109/ICCSRE.2019.8807726	conference	July 2019
An Adversarial Approach for Explainable AI in Intrusion Detection Systems Marino, Daniel L.; Wickramasinghe, Chathurika S.; Manic, Milos IECON 2018 - 44th Annual Conference of the IEEE Industrial Electronics Society https://doi.org/10.1109/IECON.2018.8591457	conference	October 2018
Crowd Management: The Overlooked Component of Smart Transportation Systems Boukerche, Azzedine; Coutinho, Rodolfo W. L. IEEE Communications Magazine, Vol. 57, Issue 4 https://doi.org/10.1109/MCOM.2019.1800641	journal	April 2019
OTIDS: A Novel Intrusion Detection System for In-vehicle Network by Using Remote Frame Lee, Hyunsung; Jeong, Seong Hoon; Kim, Huy Kang 2017 15th Annual Conference on Privacy, Security and Trust (PST) https://doi.org/10.1109/PST.2017.00017	conference	August 2017
GIDS: GAN based Intrusion Detection System for In-Vehicle Network Seo, Eunbi; Song, Hyun Min; Kim, Huy Kang 2018 16th Annual Conference on Privacy, Security and Trust (PST) https://doi.org/10.1109/PST.2018.8514157	conference	August 2018
Framework for Data Driven Health Monitoring of Cyber-Physical Systems Amarasinghe, Kasun; Wickramasinghe, Chathurika; Marino, Daniel 2018 Resilience Week (RWS) https://doi.org/10.1109/RWEEK.2018.8473535	conference	August 2018
Deep Learning-based Intrusion Detection System for Electric Vehicle Charging Station Basnet, Manoj; Hasan Ali, Mohd. 2020 2nd International Conference on Smart Power & Internet Energy Systems (SPIES) https://doi.org/10.1109/SPIES48661.2020.9243152	conference	September 2020
Adversarial Machine Learning-Industry Perspectives Siva Kumar, Ram Shankar; Nystrom, Magnus; Lambert, John 2020 IEEE Security and Privacy Workshops (SPW) https://doi.org/10.1109/SPW50608.2020.00028	conference	May 2020
VoltageIDS: Low-Level Communication Characteristics for Automotive Intrusion Detection System Choi, Wonsuk; Joo, Kyungho; Jo, Hyo Jin IEEE Transactions on Information Forensics and Security, Vol. 13, Issue 8 https://doi.org/10.1109/TIFS.2018.2812149	journal	August 2018
Big Data Analytics in Intelligent Transportation Systems: A Survey Zhu, Li; Yu, Fei Richard; Wang, Yige IEEE Transactions on Intelligent Transportation Systems, Vol. 20, Issue 1 https://doi.org/10.1109/TITS.2018.2815678	journal	January 2019
Histogram-Based Intrusion Detection and Filtering Framework for Secure and Safe In-Vehicle Networks Derhab, Abdelouahid; Belaoued, Mohamed; Mohiuddin, Irfan IEEE Transactions on Intelligent Transportation Systems, Vol. 23, Issue 3 https://doi.org/10.1109/TITS.2021.3088998	journal	March 2022
Recent Optimization Techniques for Coordinated Control of Electric Vehicles in Super Smart Power Grids Network: A State of the Art Singh, Bindeshwar; Dubey, Pankaj Kumar; Singh, S. N. 2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON) https://doi.org/10.1109/UPCON56432.2022.9986471	conference	December 2022
Cyber security issues of Internet of electric vehicles Fraiji, Yosra; Ben Azzouz, Lamia; Trojet, Wassim 2018 IEEE Wireless Communications and Networking Conference (WCNC) https://doi.org/10.1109/WCNC.2018.8377181	conference	April 2018
Fast DC Charging Infrastructures for Electric Vehicles: Overview of Technologies, Standards, and Challenges Franzese, Pasquale; Patel, Dhruvi Dhairya; Mohamed, Ahmed A. S. IEEE Transactions on Transportation Electrification, Vol. 9, Issue 3 https://doi.org/10.1109/tte.2023.3239224	journal	September 2023
Practical Black-Box Attacks against Machine Learning Papernot, Nicolas; McDaniel, Patrick; Goodfellow, Ian ASIA CCS '17: ACM Asia Conference on Computer and Communications Security, Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security https://doi.org/10.1145/3052973.3053009	conference	April 2017
Modeling inter-signal arrival times for accurate detection of CAN bus signal injection attacks: a data-driven approach to in-vehicle intrusion detection Moore, Michael R.; Bridges, Robert A.; Combs, Frank L. CISRC'17: Twelfth Annual Cyber and Information Security Research Conference, Proceedings of the 12th Annual Conference on Cyber and Information Security Research https://doi.org/10.1145/3064814.3064816	conference	April 2017
Survey of intrusion detection systems: techniques, datasets and challenges Khraisat, Ansam; Gondal, Iqbal; Vamplew, Peter Cybersecurity, Vol. 2, Issue 1 https://doi.org/10.1186/s42400-019-0038-7	journal	July 2019
Intrusion Detection System Using Deep Neural Network for In-Vehicle Network Security Kang, Min-Joo; Kang, Je-Won PLOS ONE, Vol. 11, Issue 6 https://doi.org/10.1371/journal.pone.0155781	journal	June 2016
Smart Grid Communication Networks for Electric Vehicles Empowering Distributed Energy Generation: Constraints, Challenges, and Recommendations Hasan, Mohammad Kamrul; Habib, AKM Ahasan; Islam, Shayla Energies, Vol. 16, Issue 3 https://doi.org/10.3390/en16031140	journal	January 2023
Sensor Technologies for Intelligent Transportation Systems Guerrero-Ibáñez, Juan; Zeadally, Sherali; Contreras-Castillo, Juan Sensors, Vol. 18, Issue 4 https://doi.org/10.3390/s18041212	journal	April 2018

Similar Records

Cy-Phy ADS: Cyber Physical Anomaly Detection Framework for EV Charging Systems

Journal Article · Sun Dec 31 19:00:00 EST 2023 · IEEE Transactions on Transportation Electrification (Online) · OSTI ID:2337436

Generative and Encoded Anomaly Detectors

Conference · Wed Dec 04 23:00:00 EST 2019 · OSTI ID:1765137

Improving Robustness of Spectrogram Classifiers with Neural Stochastic Differential Equations

Conference · Fri Nov 01 00:00:00 EDT 2024 · OSTI ID:2476611

Related Subjects

42 ENGINEERING
97 MATHEMATICS AND COMPUTING
Anomaly detection
Autoencoders
Deep neural networks
Electric vehicles
Explainable AI
Interpretability
Neural networks
Unsupervised learning

RX-ADS: Interpretable Anomaly Detection Using Adversarial ML for Electric Vehicle CAN Data

Citation Formats

References (33)

Similar Records

Related Subjects