{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T16:02:00Z","timestamp":1774540920140,"version":"3.50.1"},"reference-count":59,"publisher":"Association for Computing Machinery (ACM)","issue":"3","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Cyber-Phys. Syst."],"published-print":{"date-parts":[[2025,7,31]]},"abstract":"<jats:p>Vehicle-to-Everything (V2X) communication enables vehicles to communicate with other vehicles and roadside infrastructure, enhancing traffic management and improving road safety. However, the open and decentralized nature of V2X networks exposes them to various security threats, especially misbehaviors, necessitating a robust Misbehavior Detection System (MBDS). While Machine Learning (ML) has proved effective in different anomaly detection applications, the existing ML-based MBDSs have shown limitations in generalizing due to the dynamic nature of V2X and insufficient and imbalanced training data. Moreover, they are known to be vulnerable to adversarial ML attacks. On the other hand, Generative Adversarial Networks (GAN) possess the potential to mitigate the aforementioned issues and improve detection performance by synthesizing unseen samples of minority classes and utilizing them during their model training. Therefore, we propose the first application of GAN to design an MBDS that detects any misbehavior and ensures robustness against adversarial perturbation.<\/jats:p>\n          <jats:p>\n            In this article, we present several key contributions. First, we propose an advanced threat model for stealthy V2X misbehavior where the attacker can transmit malicious data and mask it using adversarial attacks to avoid detection by ML-based MBDS. We formulate two categories of adversarial attacks against the anomaly-based MBDS. Later, in the pursuit of a generalized and robust GAN-based MBDS, we train and evaluate a diverse set of Wasserstein GAN (WGAN) models and present\n            <jats:sc>Ve<\/jats:sc>\n            hicular\n            <jats:sc>GAN<\/jats:sc>\n            (\n            <jats:sc>VehiGAN<\/jats:sc>\n            ), an ensemble of multiple top-performing WGANs, which transcends the limitations of individual models and improves detection performance. We present a physics-guided data preprocessing technique that generates effective features for ML-based MBDS. In the evaluation, we leverage the state-of-the-art V2X attack simulation tool VASP to create a comprehensive dataset of V2X messages with diverse misbehaviors. Evaluation results show that in 20 out of 35 misbehaviors,\n            <jats:sc>VehiGAN<\/jats:sc>\n            outperforms the baseline and exhibits comparable detection performance in other scenarios. Particularly,\n            <jats:sc>VehiGAN<\/jats:sc>\n            excels in detecting advanced misbehaviors that manipulate multiple fields in V2X messages simultaneously, replicating unique maneuvers. Moreover,\n            <jats:sc>VehiGAN<\/jats:sc>\n            provides approximately 92% improvement in false positive rate under powerful adaptive adversarial attacks, and possesses intrinsic robustness against other adversarial attacks that target the false negative rate. Finally, we make the data and code available for reproducibility and future benchmarking, available at\n            <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/shahriar0651\/VehiGAN\">https:\/\/github.com\/shahriar0651\/VehiGAN<\/jats:ext-link>\n            .\n          <\/jats:p>","DOI":"10.1145\/3745787","type":"journal-article","created":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T06:40:41Z","timestamp":1750747241000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["<scp>VehiGAN<\/scp>\n            : Generative Adversarial Networks for Adversarially Robust V2X Misbehavior Detection Systems"],"prefix":"10.1145","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0289-8611","authenticated-orcid":false,"given":"Md Hasan","family":"Shahriar","sequence":"first","affiliation":[{"name":"Virginia Tech, Arlington, Virginia, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4416-7879","authenticated-orcid":false,"given":"Mohammad Raashid","family":"Ansari","sequence":"additional","affiliation":[{"name":"Self, Boxborough, Massachusetts, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7712-1132","authenticated-orcid":false,"given":"Jean-Philippe","family":"Monteuuis","sequence":"additional","affiliation":[{"name":"Qualcomm Technologies, Inc., Boxborough, Massachusetts, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0916-922X","authenticated-orcid":false,"given":"Md Shahedul","family":"Haque","sequence":"additional","affiliation":[{"name":"Virginia Tech, Arlington, Virginia, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0997-7888","authenticated-orcid":false,"given":"Cong","family":"Chen","sequence":"additional","affiliation":[{"name":"Qualcomm Technologies, Inc., San Diego, California, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8644-1442","authenticated-orcid":false,"given":"Jonathan","family":"Petit","sequence":"additional","affiliation":[{"name":"Qualcomm Technologies, Inc., Boxborough, Massachusetts, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3716-5768","authenticated-orcid":false,"given":"Y. Thomas","family":"Hou","sequence":"additional","affiliation":[{"name":"Virginia Tech, Blacksburg, Virginia, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2421-4623","authenticated-orcid":false,"given":"Wenjing","family":"Lou","sequence":"additional","affiliation":[{"name":"Virginia Tech, Arlington, Virginia, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,8,4]]},"reference":[{"key":"e_1_3_1_2_2","volume-title":"International Conference on Consumer Electronics-Asia (ICCE-Asia)","author":"Aliev Hayotjon","year":"2021","unstructured":"Hayotjon Aliev and HyungWon Kim. 2021. Misbehavior detection based on multi-head deep learning for V2X network security. In International Conference on Consumer Electronics-Asia (ICCE-Asia). IEEE."},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1954.10501232"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.14722\/vehiclesec.2023.23071"},{"key":"e_1_3_1_5_2","volume-title":"International Conference on Machine Learning","author":"Arjovsky Martin","year":"2017","unstructured":"Martin Arjovsky, Soumith Chintala, and L\u00e9on Bottou. 2017. Wasserstein generative adversarial networks. In International Conference on Machine Learning. PMLR."},{"key":"e_1_3_1_6_2","unstructured":"Miko\u0142aj Bi\u0144kowski Danica J. Sutherland Michael Arbel and Arthur Gretton. 2018. Demystifying MMD GANs. arXiv:1801.01401. Retrieved from https:\/\/arxiv.org\/abs\/1801.01401"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btl242"},{"key":"e_1_3_1_8_2","first-page":"100586","volume-title":"Vehicular Communications","author":"Bouchouia Mohammed Lamine","year":"2023","unstructured":"Mohammed Lamine Bouchouia, Houda Labiod, Ons Jelassi, Jean-Philippe Monteuuis, Wafa Ben Jaballah, Jonathan Petit, and Zonghua Zhang. 2023. A survey on misbehavior detection for connected and autonomous vehicles. Vehicular Communications 41 (2023), 100586."},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2797529"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","unstructured":"V2X Core Technical Committee. 2023. V2X Communications Message Set Dictionary. DOI:10.4271\/J2735_202309","DOI":"10.4271\/J2735_202309"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/0047-259X(82)90077-X"},{"key":"e_1_3_1_13_2","unstructured":"Ishan Durugkar Ian Gemp and Sridhar Mahadevan. 2016. Generative multi-adversarial networks. arXiv:1611.01673. Retrieved from https:\/\/arxiv.org\/abs\/1611.01673"},{"key":"e_1_3_1_14_2","first-page":"1893","volume-title":"IEEE Access","author":"Ercan Secil","year":"2021","unstructured":"Secil Ercan, Marwane Ayaida, and Nadhir Messai. 2021. Misbehavior detection for position falsification attacks in VANETs using machine learning. IEEE Access 10 (2021), 1893\u20131904."},{"key":"e_1_3_1_15_2","unstructured":"Crist\u00f3bal Esteban Stephanie L. Hyland and Gunnar R\u00e4tsch. 2017. Real-valued (medical) time series generation with recurrent conditional GANs. arXiv:1706.02633. Retrieved from https:\/\/arxiv.org\/abs\/1706.02633"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1093\/mnras\/225.1.155"},{"key":"e_1_3_1_17_2","article-title":"Generative adversarial nets","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in Neural Information Processing Systems.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_18_2","unstructured":"Ian J. Goodfellow Jonathon Shlens and Christian Szegedy. 2014. Explaining and harnessing adversarial examples. arXiv:1412.6572. Retrieved from https:\/\/arxiv.org\/abs\/1412.6572"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.5555\/2188385.2188410"},{"key":"e_1_3_1_20_2","article-title":"Improved training of Wasserstein GANs","author":"Gulrajani Ishaan","year":"2017","unstructured":"Ishaan Gulrajani, Faruk Ahmed, Martin Arjovsky, Vincent Dumoulin, and Aaron C. Courville. 2017. Improved training of Wasserstein GANs. In Advances in Neural Information Processing Systems.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_21_2","volume-title":"International Conference on Communications","author":"Gyawali Sohan","year":"2019","unstructured":"Sohan Gyawali and Yi Qian. 2019. Misbehavior detection using machine learning in vehicular communication networks. In International Conference on Communications. IEEE."},{"key":"e_1_3_1_22_2","volume-title":"AAAI Conference on Artificial Intelligence","author":"Han Xu","year":"2021","unstructured":"Xu Han, Xiaohui Chen, and Li-Ping Liu. 2021. Gan ensemble for anomaly detection. In AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.143.1.7063747"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2020.2987430"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3233793"},{"key":"e_1_3_1_26_2","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume":"30","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In Advances in Neural Information Processing Systems, Vol. 30.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1023\/B:AIRE.0000045502.10941.a9"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijcip.2021.100452"},{"key":"e_1_3_1_30_2","volume-title":"2020 IEEE International Conference on Communications (ICC \u201920)","author":"Kamel Joseph","year":"2020","unstructured":"Joseph Kamel, Michael Wolf, Rens W. Van Der Hei, Arnaud Kaiser, Pascal Urien, and Frank Kargl. 2020. VeReMi extension: A dataset for comparable evaluation of misbehavior detection in VANETs. In 2020 IEEE International Conference on Communications (ICC \u201920). IEEE."},{"key":"e_1_3_1_31_2","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1007\/978-1-4419-6142-6_7","article-title":"Traffic simulation with SUMO\u2013simulation of urban mobility","author":"Krajzewicz Daniel","year":"2010","unstructured":"Daniel Krajzewicz. 2010. Traffic simulation with SUMO\u2013simulation of urban mobility. In Fundamentals of Traffic Simulation, Springer, 269\u2013293.","journal-title":"Fundamentals of Traffic Simulation"},{"key":"e_1_3_1_32_2","first-page":"887","volume-title":"2023 IEEE 43rd International Conference on Distributed Computing Systems (ICDCS)","author":"Liu Zhikang","year":"2023","unstructured":"Zhikang Liu, Hongyun Xu, Yong Kuang, and Feng Li. 2023. SVMDformer: A semi-supervised vehicular misbehavior detection framework based on transformer in IoV. In 2023 IEEE 43rd International Conference on Distributed Computing Systems (ICDCS). IEEE, 887\u2013897."},{"key":"e_1_3_1_33_2","first-page":"65760","volume-title":"IEEE Access","author":"Nayeen Mahi Md Julkar","year":"2022","unstructured":"Md Julkar Nayeen Mahi, Sudipto Chaki, Shamim Ahmed, Milon Biswas, M. Shamim Kaiser, Mohammad Shahidul Islam, Mehdi Sookhak, Alistair Barros, and Md Whaiduzzaman. 2022. A review on VANET research: Perspective of recent emerging technologies. IEEE Access 10 (2022), 65760\u201365783."},{"key":"e_1_3_1_34_2","volume-title":"ACM Computer Science in Car Symposium","author":"Monteuuis Jean-Philippe","year":"2018","unstructured":"Jean-Philippe Monteuuis, Jonathan Petit, Jun Zhang, Houda Labiod, Stefano Mafrica, and Alain Servel. 2018. Attacker model for connected and automated vehicles. In ACM Computer Science in Car Symposium."},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2975822"},{"key":"e_1_3_1_36_2","unstructured":"World Health Organization. 2018. Global Status Report on Road Safety. Retrieved from https:\/\/www.who.int\/publications\/i\/item\/9789241565684"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.3390\/make2040031"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/342009.335437"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1026543900054"},{"key":"e_1_3_1_40_2","volume-title":"Global Communications Conference","author":"Sedar Roshan","year":"2022","unstructured":"Roshan Sedar, Charalampos Kalalas, Paolo Dini, Jesus Alonso-Zarate, and Francisco V\u00e1zquez-Gallego. 2022. Misbehavior detection in vehicular networks: An ensemble learning approach. In Global Communications Conference. IEEE."},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3461837"},{"key":"e_1_3_1_42_2","volume-title":"International Conference on Communications","author":"Sedar Roshan","year":"2022","unstructured":"Roshan Sedar, Charalampos Kalalas, Francisco V\u00e1zquez-Gallego, and Jesus Alonso-Zarate. 2022. Reinforcement learning based misbehavior detection in vehicular networks. In International Conference on Communications. IEEE."},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","unstructured":"Md Hasan Shahriar Mohammad Raashid Ansari Jean-Philippe Monteuuis Cong Chen Jonathan Petit Y. Thomas Hou and Wenjing Lou. 2024. MisbehaviorX: Comprehensive V2X misbehavior detection dataset enabled by the V2X application spoofing platform. DOI:10.21227\/s44z-8616","DOI":"10.21227\/s44z-8616"},{"key":"e_1_3_1_44_2","doi-asserted-by":"crossref","first-page":"1294","DOI":"10.1109\/ICDCS60910.2024.00122","volume-title":"2024 IEEE 44th International Conference on Distributed Computing Systems (ICDCS)","author":"Shahriar Md Hasan","year":"2024","unstructured":"Md Hasan Shahriar, Mohammad Raashid Ansari, Jean-Philippe Monteuuis, Cong Chen, Jonathan Petit, Y. Thomas Hou, and Wenjing Lou. 2024. VehiGAN: Generative adversarial networks for adversarially robust V2X misbehavior detection systems. In 2024 IEEE 44th International Conference on Distributed Computing Systems (ICDCS). IEEE, 1294\u20131305."},{"key":"e_1_3_1_45_2","volume-title":"2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC)","author":"Shahriar Md Hasan","year":"2020","unstructured":"Md Hasan Shahriar, Nur Imtiazul Haque, Mohammad Ashiqur Rahman, and Miguel Alonso. 2020. G-IDS: Generative adversarial networks assisted intrusion detection system. In 2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC). IEEE."},{"issue":"6","key":"e_1_3_1_46_2","doi-asserted-by":"crossref","first-page":"4991","DOI":"10.1109\/JIOT.2020.3035035","article-title":"A machine-learning-based data-centric misbehavior detection model for internet of vehicles","volume":"8","author":"Sharma Prinkle","year":"2020","unstructured":"Prinkle Sharma and Hong Liu. 2020. A machine-learning-based data-centric misbehavior detection model for internet of vehicles. IEEE Internet of Things Journal 8, 6 (2020), 4991\u20134999.","journal-title":"IEEE Internet of Things Journal"},{"key":"e_1_3_1_47_2","volume-title":"IEEE Foundations and New Directions of Data Mining Workshop","author":"Shyu Mei-Ling","year":"2003","unstructured":"Mei-Ling Shyu, Shu-Ching Chen, Kanoksri Sarinnapakorn, and LiWu Chang. 2003. A novel anomaly detection scheme based on principal component classifier. In IEEE Foundations and New Directions of Data Mining Workshop. IEEE Press."},{"key":"e_1_3_1_48_2","unstructured":"Santokh Singh. 2018. Critical Reasons for Crashes Investigated in the National Motor Vehicle Crash Causation Survey. Retrieved from https:\/\/crashstats.nhtsa.dot.gov\/Api\/Public\/Publication\/812506"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177730256"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3317549.3323406"},{"key":"e_1_3_1_51_2","volume-title":"Recent Advances in Network Simulation: The OMNeT++ Environment and Its Ecosystem","author":"Sommer Christoph","year":"2019","unstructured":"Christoph Sommer, David Eckhoff, Alexander Brummer, Dominik S. Buse, Florian Hagenauer, Stefan Joerer, and Michele Segata. 2019. Veins: The open source vehicular network simulation framework. In Recent Advances in Network Simulation: The OMNeT++ Environment and Its Ecosystem."},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","unstructured":"V2X Core Technical Committee. 2020. On-Board System Requirements for V2V Safety Communications. DOI:10.4271\/J2945\/1_202004","DOI":"10.4271\/J2945\/1_202004"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3292055"},{"key":"e_1_3_1_56_2","volume-title":"14th International Conference on Security and Privacy in Communication Networks (SecureComm \u201918), Part I","author":"Der Heijden Rens W. Van","year":"2018","unstructured":"Rens W. Van Der Heijden, Thomas Lukaseder, and Frank Kargl. 2018. VeReMi: A dataset for comparable evaluation of misbehavior detection in VANETs. In 14th International Conference on Security and Privacy in Communication Networks (SecureComm \u201918), Part I. Springer."},{"key":"e_1_3_1_57_2","volume-title":"Modeling and Tools for Network Simulation","author":"Varga Andras","year":"2010","unstructured":"Andras Varga. 2010. OMNeT++. In Modeling and Tools for Network Simulation. Springer."},{"key":"e_1_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.6028\/NIST.AI.100-2e2023"},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.12.093"},{"key":"e_1_3_1_60_2","unstructured":"Hongyang Zhang Susu Xu Jiantao Jiao Pengtao Xie Ruslan Salakhutdinov and Eric P. Xing. 2018. Stackelberg GAN: Towards provable minimax equilibrium via multi-generator architectures. arXiv:1811.08010. Retrieved from https:\/\/arxiv.org\/abs\/1811.08010"}],"container-title":["ACM Transactions on Cyber-Physical Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3745787","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T15:53:51Z","timestamp":1754322831000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3745787"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,31]]},"references-count":59,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,7,31]]}},"alternative-id":["10.1145\/3745787"],"URL":"https:\/\/doi.org\/10.1145\/3745787","relation":{},"ISSN":["2378-962X","2378-9638"],"issn-type":[{"value":"2378-962X","type":"print"},{"value":"2378-9638","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,31]]},"assertion":[{"value":"2024-11-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-30","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}