{"type":"ScholarlyArticle","title":"Imitative Attacker Deception in Stackelberg Security Games","authors":[{"name":"Thanh Nguyen","slug":"thanh-nguyen","given":"Thanh","family":"Nguyen","affiliation":"University of Oregon"},{"name":"Haifeng Xu","slug":"haifeng-xu","given":"Haifeng","family":"Xu","affiliation":"Harvard University"}],"abstract":"To address the challenge of uncertainty regarding the attacker’s payoffs, capabilities, and other characteristics, recent work in security games has focused on learning the optimal defense strategy from observed attack data. This raises a natural concern that the strategic attacker may mislead the defender by deceptively reacting to the learning algorithms.\r\nThis paper focuses on understanding how such attacker deception affects the game equilibrium. We examine a basic deception strategy termed imitative deception, in which the attacker simply pretends to have a different payoff assuming his true payoff is unknown to the defender. We provide a clean characterization about the game equilibrium as well as optimal algorithms to compute the equilibrium. Our experiments illustrate significant defender loss due to imitative attacker deception, suggesting the potential side effect of learning from the attacker.","doi":"10.24963/ijcai.2019/75","url":"https://ijcai.org/proceedings/2019/75","pdf":"https://ijcai.org/proceedings/2019/0075.pdf","markdown":"https://ijcai.org/proceedings/2019/75.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/75","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Agent-based and Multi-agent Systems","track":"Main track","number":75,"pages":{"first":528,"last":534},"keywords":["Agent-based and Multi-agent Systems: Multi-agent Planning","Agent-based and Multi-agent Systems: Noncooperative Games"],"videos":[],"references":[{"position":1,"raw":"[Balcan et al., 2015] Maria-Florina Balcan, Avrim Blum, Nika Haghtalab, and Ariel D. Procaccia. Commitment without regrets: Online learning in Stackelberg security games. In 16th ACM Conference on Economics and Com- putation, pages 61-78, 2015.","title":"Commitment without regrets: Online learning in Stackelberg security games","authors":"Maria-Florina Balcan, Avrim Blum, Nika Haghtalab, Ariel D Procaccia","year":"2015","venue":"16th ACM Conference on Economics and Computation","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Barreno et al., 2006] Marco Barreno, Blaine Nelson, Rus- sell Sears, Anthony D. Joseph, and J. Doug Tygar. Can machine learning be secure? In ACM Symposium on Infor- mation, Computer and Communications Security, 2006.","title":"Can machine learning be secure?","authors":"Marco Barreno, Blaine Nelson, Russell Sears, Anthony D Joseph, J Doug Tygar","year":"2006","venue":"ACM Symposium on Information","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Barreno et al., 2010] Marco Barreno, Blaine Nelson, An- thony D. Joseph, and J. D. Tygar. The security of machine learning. Machine Learning, 81(2):121-148, 2010.","title":"The security of machine learning","authors":"Marco Barreno, Blaine Nelson, Anthony D Joseph, J D Tygar","year":"2010","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Blum et al., 2014] Avrim Blum, Nika Haghtalab, and Ariel D. Procaccia. Learning optimal commitment to over- come insecurity. In Advances in Neural Information Pro- cessing Systems, pages 1826-1834, 2014.","title":"Learning optimal commitment to overcome insecurity","authors":"Avrim Blum, Nika Haghtalab, Ariel D Procaccia","year":"2014","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Brückner and Scheffer, 2011] Michael Brückner and Tobias Scheffer. Stackelberg games for adversarial prediction problems. In ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2011.","title":"Stackelberg games for adversarial prediction problems","authors":"Scheffer Brückner, Michael Brückner, Tobias Scheffer","year":"2011","venue":"ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Brückner et al., 2012] Michael Brückner, Christian Kan- zow, and Tobias Scheffer. Static prediction games for ad- versarial learning problems. Journal of Machine Learning Research, 13:2617-2654, 2012.","title":"Static prediction games for adversarial learning problems","authors":"Michael Brückner, Christian Kanzow, Tobias Scheffer","year":"2012","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Fraunholz et al., 2018] D. Fraunholz, S. D. Anton, C. Lipps, D. Reti, D. Krohmer, F. Pohl, M. Tammen, and H. D. Schotten. Demystifying deception technology: A survey. arXiv preprint arXiv:1804.06196, 2018.","title":"Demystifying deception technology: A survey","authors":"D Fraunholz, S D Anton, C Lipps, D Reti, D Krohmer, F Pohl, M Tammen, H D Schotten","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Gholami et al., 2017] S. Gholami, B. Ford, F. Fang, A. Plumptre, M. Tambe, M. Driciru, F. Wanyama, A. Rwetsiba, M. Nsubaga, and J. Mabonga. Taking it for a test drive: a hybrid spatio-temporal model for wildlife poaching prediction evaluated through a controlled field test. In European Conference on Machine Learning, 2017.","title":"Taking it for a test drive: a hybrid spatio-temporal model for wildlife poaching prediction evaluated through a controlled field test","authors":"S Gholami, B Ford, F Fang, A Plumptre, M Tambe, M Driciru, F Wanyama, A Rwetsiba, M Nsubaga, J Mabonga","year":"2017","venue":"European Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Guo et al., 2017] Qingyu Guo, Bo An, Branislav Bosan- sky, and C. Kiekintveld. Comparing strategic secrecy and Stackelberg commitment in security games. In 26th Inter- national Joint Conference on Artificial Intelligence, 2017.","title":"Comparing strategic secrecy and Stackelberg commitment in security games","authors":"Qingyu Guo, Bo An, Branislav Bosansky, C Kiekintveld","year":"2017","venue":"26th International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2017/516"},{"position":10,"raw":"[Haghtalab et al., 2016] Nika Haghtalab, Fei Fang, Thanh Hong Nguyen, Arunesh Sinha, Ariel D. Pro- caccia, and Milind Tambe. Three strategies to success: Learning adversary models in security games. In 25th International Joint Conference on Artificial Intelligence, pages 308-314, 2016.","title":"Three strategies to success: Learning adversary models in security games","authors":"Nika Haghtalab, Fei Fang, Thanh Hong Nguyen, Arunesh Sinha, Ariel D Procaccia, Milind Tambe","year":"2016","venue":"25th International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2016/51"},{"position":11,"raw":"[Kar et al., 2017] D. Kar, B. Ford, S. Gholami, F. Fang, A. Plumptre, M. Tambe, M. Driciru, F. Wanyama, A. Rwetsiba, and M. Nsubaga. Cloudy with a chance of poaching: Adversary behavior modeling and forecasting with real-world poaching data. In 16th International Con- ference on Autonomous Agents and Multi-Agent Systems, 2017.","title":"Cloudy with a chance of poaching: Adversary behavior modeling and forecasting with real-world poaching data","authors":"D Kar, B Ford, S Gholami, F Fang, A Plumptre, M Tambe, M Driciru, F Wanyama, A Rwetsiba, M Nsubaga","year":"2017","venue":"16th International Conference on Autonomous Agents and Multi-Agent Systems","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kiekintveld et al., 2009] Christopher Kiekintveld, Manish Jain, Jason Tsai, James Pita, Fernando Ordóñez, and Milind Tambe. Computing optimal randomized resource allocations for massive security games. In 8th Interna- tional Conference on Autonomous Agents and Multiagent Systems-Volume 1, pages 689-696, 2009.","title":"Computing optimal randomized resource allocations for massive security games","authors":"Christopher Kiekintveld, Manish Jain, Jason Tsai, James Pita, Fernando Ordóñez, Milind Tambe","year":"2009","venue":"8th International Conference on Autonomous Agents and Multiagent Systems","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Letchford et al., 2009] Joshua Letchford, Vincent Conitzer, and Kamesh Munagala. Learning and approximating the optimal strategy to commit to. In International Symposium on Algorithmic Game Theory, pages 250-262, 2009.","title":"Learning and approximating the optimal strategy to commit to","authors":"Joshua Letchford, Vincent Conitzer, Kamesh Munagala","year":"2009","venue":"International Symposium on Algorithmic Game Theory","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Lowd and Meek, 2005] Daniel Lowd and Christopher Meek. Adversarial learning. In ACM SIGKDD Inter- national Conference on Knowledge Discovery in Data Mining, pages 641-647, 2005.","title":"Adversarial learning","authors":"Meek Lowd, Daniel Lowd, Christopher Meek","year":"2005","venue":"ACM SIGKDD International Conference on Knowledge Discovery in Data Mining","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Marecki et al., 2012] Janusz Marecki, Gerry Tesauro, and Richard Segal. Playing repeated Stackelberg games with unknown opponents. In 11th International Conference on Autonomous Agents and Multiagent Systems, 2012.","title":"Playing repeated Stackelberg games with unknown opponents","authors":"Janusz Marecki, Gerry Tesauro, Richard Segal","year":"2012","venue":"11th International Conference on Autonomous Agents and Multiagent Systems","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Nguyen et al., 2016] T. H. Nguyen, A. Sinha, S. Gho- lami, A. Plumptre, L. Joppa, M. Tambe, M. Driciru, F. Wanyama, A. Rwetsiba, R. Critchlow, et al. Capture: A new predictive anti-poaching tool for wildlife protection. In 15th International Conference on Autonomous Agents and Multi-Agent Systems, pages 767-775, 2016.","title":"Capture: A new predictive anti-poaching tool for wildlife protection","authors":"T H Nguyen, A Sinha, S Gholami, A Plumptre, L Joppa, M Tambe, M Driciru, F Wanyama, A Rwetsiba, R Critchlow","year":"2016","venue":"15th International Conference on Autonomous Agents and Multi-Agent Systems","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Nguyen et al., 2019] Thanh H Nguyen, Yongzhao Wang, Arunesh Sinha, and Michael P Wellman. Deception in finitely repeated security games. In 33th AAAI Conference on Artificial Intelligence, 2019.","title":"Deception in finitely repeated security games","authors":"Yongzhao Thanh H Nguyen, Arunesh Wang, Michael P Sinha, Wellman","year":"2019","venue":"33th AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Peng et al., 2019] B. Peng, Weiran Shen, Pingzhong Tang, and Song Zuo. Learning optimal strategies to commit to. In 33th AAAI Conference on Artificial Intelligence, 2019.","title":"Learning optimal strategies to commit to","authors":"B Peng, Weiran Shen, Pingzhong Tang, Song Zuo","year":"2019","venue":"33th AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Rabinovich et al., 2015] Zinovi Rabinovich, Albert Xin Jiang, Manish Jain, and Haifeng Xu. Information disclo- sure as a means to security. In 14th International Con- ference on Autonomous Agents and Multi-Agent Systems, pages 645-653, 2015.","title":"Information disclosure as a means to security","authors":"Rabinovich","year":"2015","venue":"14th International Conference on Autonomous Agents and Multi-Agent Systems","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Tambe, 2011] Milind Tambe. Security and game theory: al- gorithms, deployed systems, lessons learned. Cambridge University Press, 2011.","title":"Security and game theory: algorithms, deployed systems, lessons learned","authors":"Milind Tambe","year":"2011","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Xu et al., 2015] Haifeng Xu, Zinovi Rabinovich, Shaddin Dughmi, and Milind Tambe. Exploring information asym- metry in two-stage security games. In 29th AAAI Confer- ence on Artificial Intelligence, pages 1057-1063, 2015.","title":"Exploring information asymmetry in two-stage security games","authors":"Haifeng Xu, Zinovi Rabinovich, Shaddin Dughmi, Milind Tambe","year":"2015","venue":"29th AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Xu et al., 2016] Haifeng Xu, Long Tran-Thanh, and Nicholas R. Jennings. Playing repeated security games with no prior knowledge. In 15th International Confer- ence on Autonomous Agents and Multi-Agent Systems, pages 104-112, 2016.","title":"Playing repeated security games with no prior knowledge","authors":"Haifeng Xu, Long Tran-Thanh, Nicholas R Jennings","year":"2016","venue":"15th International Conference on Autonomous Agents and Multi-Agent Systems","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Yin et al., 2010] Zhengyu Yin, Dmytro Korzhyk, Christo- pher Kiekintveld, Vincent Conitzer, and Milind Tambe. Stackelberg vs. Nash in security games: Interchangeabil- ity, equivalence, and uniqueness. In 9th International Con- ference on Autonomous Agents and Multi-Agent Systems, pages 1139-1146, 2010.","title":"Stackelberg vs. Nash in security games: Interchangeability, equivalence, and uniqueness","authors":"Dmytro Zhengyu Yin, Christopher Korzhyk, Vincent Kiekintveld, Milind Conitzer, Tambe","year":"2010","venue":"9th International Conference on Autonomous Agents and Multi-Agent Systems","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Zhuang et al., 2010] Jun Zhuang, Vicki M. Bier, and Oguzhan Alagoz. Modeling secrecy and deception in a multi-period attacker-defender signaling game. European Journal of Operational Research, 203:409-418, 2010.","title":"Modeling secrecy and deception in a multi-period attacker-defender signaling game","authors":"Zhuang","year":"2010","venue":"European Journal of Operational Research","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}