{"type":"ScholarlyArticle","title":"Adversarial Regression for Detecting Attacks in Cyber-Physical Systems","authors":[{"name":"Amin Ghafouri","slug":"amin-ghafouri","given":"Amin","family":"Ghafouri","affiliation":"Cruise Automation , San Francisco , CA"},{"name":"Yevgeniy Vorobeychik","slug":"yevgeniy-vorobeychik","given":"Yevgeniy","family":"Vorobeychik","affiliation":"Electrical Engineering and Computer Science , Vanderbilt University , Nashville , TN"},{"name":"Xenofon Koutsoukos","slug":"xenofon-koutsoukos","given":"Xenofon","family":"Koutsoukos","affiliation":"Electrical Engineering and Computer Science , Vanderbilt University , Nashville , TN"}],"abstract":"Attacks in cyber-physical systems (CPS) which manipulate sensor\r\nreadings can cause enormous physical damage if undetected.\r\nDetection of attacks on sensors \r\nis crucial to mitigate this issue.\r\nWe study supervised regression as a means to detect anomalous sensor\r\nreadings, where each sensor's measurement is predicted as a function\r\nof other sensors.\r\nWe show that several common learning approaches in this context\r\nare still vulnerable to stealthy attacks, which carefully\r\nmodify readings of compromised sensors to cause desired damage while\r\nremaining undetected.\r\nNext, we model the interaction between the CPS defender and attacker\r\nas a Stackelberg game in which the defender chooses detection\r\nthresholds, while the attacker deploys a stealthy attack in response.\r\nWe present a heuristic algorithm for finding an approximately optimal threshold for\r\nthe defender in this game, and show that it increases system\r\nresilience to attacks without significantly increasing the false alarm rate.","doi":"10.24963/ijcai.2018/524","url":"https://ijcai.org/proceedings/2018/524","pdf":"https://ijcai.org/proceedings/2018/0524.pdf","markdown":"https://ijcai.org/proceedings/2018/524.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/524","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Multidisciplinary Topics and Applications","track":"Main track","number":524,"pages":{"first":3769,"last":3775},"keywords":["Multidisciplinary Topics and Applications: Security and Privacy","Machine Learning Applications: Applications of Supervised Learning"],"videos":[],"references":[{"position":1,"raw":"[Bathelt et al., 2015] Andreas Bathelt, N Lawrence Ricker, and Mohieddine Jelali. Revision of the tennessee east- man process model. IFAC-PapersOnLine, 48(8):309-314, 2015.","title":"Revision of the tennessee eastman process model","authors":"Bathelt","year":"2015","venue":"IFAC-PapersOnLine","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Biggio et al., 2010] Battista Biggio, Giorgio Fumera, and Fabio Roli. Multiple classifier systems for robust classifier design in adversarial environments. International Jour- nal of Machine Learning and Cybernetics, 1(1-4):27-41, 2010.","title":"Multiple classifier systems for robust classifier design in adversarial environments","authors":"Battista Biggio, Giorgio Fumera, Fabio Roli","year":"2010","venue":"International Journal of Machine Learning and Cybernetics","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Biggio et al., 2014] Battista Biggio, Giorgio Fumera, and Fabio Roli. Security evaluation of pattern classifiers un- der attack. IEEE Transactions on Knowledge and Data Engineering, 26(4):984-996, 2014.","title":"Security evaluation of pattern classifiers under attack","authors":"Battista Biggio, Giorgio Fumera, Fabio Roli","year":"2014","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cárdenas et al., 2011] Alvaro A Cárdenas, Saurabh Amin, Zong-Syun Lin, Yu-Lun Huang, Chi-Yen Huang, and Shankar Sastry. Attacks against process control systems: risk assessment, detection, and response. In Proceedings of the 6th ACM symposium on information, computer and communications security, pages 355-366. ACM, 2011.","title":"Attacks against process control systems: risk assessment, detection, and response","authors":"Saurabh Alvaro A Cárdenas, Zong-Syun Amin, Yu-Lun Lin, Chi-Yen Huang, Shankar Huang, Sastry","year":"2011","venue":"Proceedings of the 6th ACM symposium on information, computer and communications security","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Dalvi et al., 2004] Nilesh Dalvi, Pedro Domingos, Sumit Sanghai, Deepak Verma, et al. Adversarial classifica- tion. In Proceedings of the tenth ACM SIGKDD Interna- tional Conference on Knowledge discovery and data min- ing, pages 99-108. ACM, 2004.","title":"Adversarial classification","authors":"Nilesh Dalvi, Pedro Domingos, Sumit Sanghai, Deepak Verma","year":"2004","venue":"Proceedings of the tenth ACM SIGKDD International Conference on Knowledge discovery and data mining","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Downs and Vogel, 1993] James J Downs and Ernest F Vo- gel. A plant-wide industrial process control problem. Computers & chemical engineering, 17(3):245-255, 1993.","title":"A plant-wide industrial process control problem","authors":"J James, Ernest F Downs, Vogel","year":"1993","venue":"Computers & chemical engineering","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Ghafouri et al., 2016] Amin Ghafouri, Waseem Abbas, Aron Laszka, Yevgeniy Vorobeychik, and Xenofon Kout- soukos. Optimal thresholds for anomaly-based intrusion detection in dynamical environments. In International Conference on Decision and Game Theory for Security, pages 415-434. Springer, 2016.","title":"Optimal thresholds for anomaly-based intrusion detection in dynamical environments","authors":"Amin Ghafouri, Waseem Abbas, Aron Laszka, Yevgeniy Vorobeychik, Xenofon Koutsoukos","year":"2016","venue":"International Conference on Decision and Game Theory for Security","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Ghafouri et al., 2017] Amin Ghafouri, Aron Laszka, Ab- hishek Dubey, and Xenofon Koutsoukos. Optimal detec- tion of faulty traffic sensors used in route planning. In In- ternational Workshop on Science of Smart City Operations and Platforms Engineering (SCOPE), pages 1-6, 2017.","title":"Optimal detection of faulty traffic sensors used in route planning","authors":"Ghafouri","year":"2017","venue":"ternational Workshop on Science of Smart City Operations and Platforms Engineering (SCOPE)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Goodfellow et al., 2015] Ian J Goodfellow, Jonathon Shlens, and Christian Szegedy. Explaining and harnessing adversarial examples. In International Conference on Learning Representations, 2015.","title":"Explaining and harnessing adversarial examples","authors":"Ian J Goodfellow, Jonathon Shlens, Christian Szegedy","year":"2015","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Grosshans et al., 2013] Michael Grosshans, Christoph Sawade, Michael Brückner, and Tobias Scheffer. Bayesian games for adversarial regression problems. In International Conference on International Conference on Machine Learning, pages 55-63, 2013.","title":"Bayesian games for adversarial regression problems","authors":"Michael Grosshans, Christoph Sawade, Michael Brückner, Tobias Scheffer","year":"2013","venue":"International Conference on International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Junejo and Goh, 2016] Khurum Nazir Junejo and Jonathan Goh. Behaviour-based attack detection and classifica- tion in cyber physical systems using machine learning. In Proceedings of the 2nd ACM International Workshop on Cyber-Physical System Security, pages 34-43. ACM, 2016.","title":"Behaviour-based attack detection and classification in cyber physical systems using machine learning","authors":"Goh ; Junejo, Nazir Khurum, Jonathan Junejo, Goh","year":"2016","venue":"Proceedings of the 2nd ACM International Workshop on Cyber-Physical System Security","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Li and Vorobeychik, 2014] Bo Li and Yevgeniy Vorobey- chik. Feature cross-substitution in adversarial classifica- tion. In Neural Information Processing Systems, pages 2087-2095, 2014.","title":"Feature cross-substitution in adversarial classification","authors":"Bo Li, Yevgeniy Vorobeychik","year":"2014","venue":"Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Li and Vorobeychik, 2018] Bo Li and Yevgeniy Vorobey- chik. Evasion-robust classification on binary domains. ACM Transactions on Knowledge Discovery from Data, 2018. to appear.","title":"Evasion-robust classification on binary domains","authors":"Bo Li, Yevgeniy Vorobeychik","year":"2018","venue":"ACM Transactions on Knowledge Discovery from Data","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Lowd and Meek, 2005] Daniel Lowd and Christopher Meek. Adversarial learning. In Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining, pages 641-647. ACM, 2005.","title":"Adversarial learning","authors":"Meek Lowd, Daniel Lowd, Christopher Meek","year":"2005","venue":"Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Nader et al., 2014] Patric Nader, Paul Honeine, and Pierre Beauseroy. {l p }-norms in one-class classification for in- trusion detection in scada systems. IEEE Transactions on Industrial Informatics, 10(4):2308-2317, 2014.","title":"{l p }-norms in one-class classification for intrusion detection in scada systems","authors":"Patric Nader, Paul Honeine, Pierre Beauseroy","year":"2014","venue":"IEEE Transactions on Industrial Informatics","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Ricker, 1996] N Lawrence Ricker. Decentralized control of the tennessee eastman challenge process. Journal of Pro- cess Control, 6(4):205-221, 1996.","title":"Decentralized control of the tennessee eastman challenge process","authors":"Lawrence Ricker","year":"1996","venue":"Journal of Process Control","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Urbina et al., 2016] David I Urbina, Jairo A Giraldo, Al- varo A Cardenas, Nils Ole Tippenhauer, Junia Valente, Mustafa Faisal, Justin Ruths, Richard Candell, and Hen- rik Sandberg. Limiting the impact of stealthy attacks on industrial control systems. In Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communica- tions Security, pages 1092-1105. ACM, 2016.","title":"Limiting the impact of stealthy attacks on industrial control systems","authors":"Jairo A David I Urbina, Alvaro A Giraldo, Nils Ole Cardenas, Junia Tippenhauer, Mustafa Valente, Justin Faisal, Richard Ruths, Henrik Candell, Sandberg","year":"2016","venue":"Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Vorobeychik and Li, 2014] Yevgeniy Vorobeychik and Bo Li. Optimal randomized classification in adversarial settings. In International Conference on Autonomous Agents and Multiagent Systems, pages 485-492, 2014.","title":"Optimal randomized classification in adversarial settings","authors":"Li ; Vorobeychik, Yevgeniy Vorobeychik, Bo Li","year":"2014","venue":"International Conference on Autonomous Agents and Multiagent Systems","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}