SpringerLink
Log in

Game Theoretical Adversarial Deep Learning

  • Chapter
  • First Online:
Adversarial Machine Learning

  • 1182 Accesses

Abstract

This chapter summarizes the game theoretical strategies for generating adversarial manipulations. The adversarial learning objective for our adversaries is assumed to be to inject small changes into the data distributions, defined over positive and negative class labels, to the extent that deep learning subsequently misclassifies the data distribution. Thus, the theoretical goal of our adversarial deep learning process becomes one of determining whether a manipulation of the input data has reached a learner decision boundary, i.e., where too many positive labels have become negative labels. The adversarial data is generated by solving for optimal attack policies in Stackelberg games where adversaries target the misclassification performance of deep learning. Sequential game theoretical formulations can model the interaction between an intelligent adversary and a deep learning model to generate adversarial manipulations by solving a two-player sequential non-cooperative Stackelberg game where each player’s payoff function increases with interactions to a local optimum. With a stochastic game theoretical formulation, we can then extend the two-player Stackelberg game into a multiplayer Stackelberg game with stochastic payoff functions for the adversaries. Both versions of the game are resolved through the Nash equilibrium, which refers to a pair of strategies in which there is no incentive for either the learner or the adversary to deviate from their optimal strategy. We can then explore adversaries who optimize variational payoff functions via data randomization strategies on deep learning designed for multi-label classification tasks. Similarly, the outcome of these investigations is an algorithm design that solves a variable-sum two-player sequential Stackelberg game with new Nash equilibria. The adversary manipulates variational parameters in the input data to mislead the learning process of the deep learning, so it misclassifies the original class labels as the targeted class labels. The ideal variational adversarial manipulation is the minimum change needed to the adversarial cost function of encoded data that will result in the deep learning incorrectly labeling the decoded data. The optimal manipulations are due to stochastic optima in non-convex best response strategies. The adversarial data generated by this variant of the Stackelberg games simulates continuous interactions with the classifier’s learning processes as opposed to one-time interactions. The learning process of the CNNs can be manipulated by an adversary at the input data level as well as the generated data level. We can then retrain the original deep learning model on the manipulated data to give rise to a secure adversarial deep learning model that is robust to subsequent performance vulnerabilities from game theoretical adversaries. Alternative hypotheses for such adversarial data mining in the game theoretical adversarial deep learning strategies are provided in cybersecurity applications with machine learning that is designed for security requirements. The game theoretical solution concepts lead to a deep neural network that is robust to subsequent data manipulation by a game theoretical adversary. This promising result suggests that learning algorithms based on game theoretical modeling and mathematical optimization are a significantly better approach to building more secure deep learning models.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
EUR 29.95
Price includes VAT (Germany)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
EUR 139.09
Price includes VAT (Germany)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
EUR 181.89
Price includes VAT (Germany)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free ship** worldwide - see info
Hardcover Book
EUR 181.89
Price includes VAT (Germany)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free ship** worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. J. V. Alain Bensoussan, Jens Frehse, Nash and stackelberg differential games, Chinese Annals of Mathematics, Series B, 33 (2012), pp. 317–332.

    Google Scholar 

  2. T. Alpcan, B. I. P. Rubinstein, and C. Leckie, Large-scale strategic games and adversarial machine learning, in 2016 IEEE 55th Conference on Decision and Control, CDC, IEEE, Dec 2016, pp. 4420–4426.

    Google Scholar 

  3. T. Alpcan, B. I. P. Rubinstein, and C. Leckie, Large-scale strategic games and adversarial machine learning, in 2016 IEEE 55th Conference on Decision and Control (CDC), 2016.

    Google Scholar 

  4. K. Asif, W. **ng, S. Behpour, and B. D. Ziebart, Adversarial cost-sensitive classification, in Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence, UAI’15, Arlington, Virginia, USA, 2015, AUAI Press, pp. 92–101.

    Google Scholar 

  5. D. Balduzzi, Grammars for games: A gradient-based, game-theoretic framework for optimization in deep learning, Frontiers Robotics AI, 2 (2016), p. 39.

    Article  Google Scholar 

  6. T. Basar and J. Moon, Riccati equations in nash and stackelberg differential and dynamic games, IFAC-PapersOnLine, 50 (2017), pp. 9547–9554. 20th IFAC World Congress.

    Google Scholar 

  7. A. Bear and F. Cushman, Loss functions modulate the optimal bias-variance trade-off, in CogSci, cognitivesciencesociety.org, 2020.

    Google Scholar 

  8. C. Bector and S. Chandra, Fuzzy Mathematical Programming and Fuzzy Matrix Games, vol. 169, 01 2005.

    Google Scholar 

  9. E. Begoli and J. Horey, Design principles for effective knowledge discovery from big data, in 2012 Joint Working IEEE/IFIP Conference on Software Architecture and European Conference on Software Architecture, 2012, pp. 215–218.

    Google Scholar 

  10. M. Belkin, D. J. Hsu, S. Ma, and S. Mandal, Reconciling modern machine learning practice and the classical bias-variance trade-off, Proceedings of the National Academy of Sciences, 116 (2019), pp. 15849–15854.

    Article  MathSciNet  MATH  Google Scholar 

  11. L. Bianchi, M. Dorigo, L. M. Gambardella, and W. J. Gutjahr, A survey on metaheuristics for stochastic combinatorial optimization, Natural Computing: An International Journal, 8 (2009).

    Google Scholar 

  12. B. Biggio, G. Fumera, and F. Roli, Adversarial pattern classification using multiple classifiers and randomisation, in Structural, Syntactic, and Statistical Pattern Recognition, N. da Vitoria Lobo, T. Kasparis, F. Roli, J. T. Kwok, M. Georgiopoulos, G. C. Anagnostopoulos, and M. Loog, eds., Berlin, Heidelberg, 2008, Springer Berlin Heidelberg, pp. 500–509.

    Google Scholar 

  13. ——, Poisoning attacks against support vector machines, in Proceedings of the 29th International Coference on International Conference on Machine Learning, ICML’12, USA, 2012, Omnipress, pp. 1467–1474.

    Google Scholar 

  14. A. Blum, J. Morgenstern, A. Sharma, and A. Smith, Privacy-preserving public information for sequential games, in Proceedings of the 2015 Conference on Innovations in Theoretical Computer Science, ITCS ’15, New York, NY, USA, 2015, Association for Computing Machinery.

    Google Scholar 

  15. B. Bohrer and A. Platzer, Structured proofs for adversarial cyber-physical systems, ACM Trans. Embed. Comput. Syst., 20 (2021).

    Google Scholar 

  16. G. Bonanno, Epistemic foundations of game theory, Working Papers 106, University of California, Davis, Department of Economics, June 2014.

    Google Scholar 

  17. M. Bowling and M. Veloso, An analysis of stochastic game theory for multiagent reinforcement learning, Technical report CMU-CS-00-165, Computer Science Department, Carnegie Mellon University, 2000.

    Google Scholar 

  18. M. Bowling and M. Veloso, Rational and convergent learning in stochastic games, in Proceedings of the 17th International Joint Conference on Artificial Intelligence - Volume 2, IJCAI’01, San Francisco, CA, USA, 2001, Morgan Kaufmann Publishers Inc.

    Google Scholar 

  19. M. Brand and D. L. Dowe, The imp game: Learnability, approximability and adversarial learning beyond\(\sigma ^0_1\), J. Log. Comput., 27 (2017), pp. 2171–2192.

    Google Scholar 

  20. A. Bressan, Noncooperative differential games, Milan Journal of Mathematics, 79 (2011), pp. 357–427.

    Article  MathSciNet  MATH  Google Scholar 

  21. M. Brückner, Prediction games: machine learning in the presence of an adversary, PhD thesis, University of Potsdam, 2012.

    Google Scholar 

  22. M. Brückner, C. Kanzow, and T. Scheffer, Static prediction games for adversarial learning problems, J. Mach. Learn. Res., (2012).

    Google Scholar 

  23. M. Bruckner and T. Scheffer, Stackelberg games for adversarial prediction problems, in Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’11, New York, NY, USA, 2011, Association for Computing Machinery, p. 547–555.

    Google Scholar 

  24. S. Bulo and M. Pelillo, A game-theoretic approach to hypergraph clustering, in Advances in Neural Information Processing Systems, Y. Bengio, D. Schuurmans, J. Lafferty, C. Williams, and A. Culotta, eds., vol. 22, Curran Associates, Inc., 2009.

    Google Scholar 

  25. Y. Cai, O. Candogan, C. Daskalakis, and C. Papadimitriou, Zero-sum polymatrix games: A generalization of minmax, Mathematics of Operations Research, 41 (2016), pp. 648–655.

    Article  MathSciNet  MATH  Google Scholar 

  26. Z. Cai, Z. **ong, H. Xu, P. Wang, W. Li, and Y. Pan, Generative adversarial networks: A survey toward private and secure applications, ACM Comput. Surv., 54 (2021).

    Google Scholar 

  27. C. F. Camerer, T.-H. Ho, and J. K. Chong, Behavioural Game Theory: Thinking, Learning and Teaching, in Advances in Understanding Strategic Behaviour, S. Huck, ed., Palgrave Macmillan Books, Palgrave Macmillan, 2004, ch. 8, pp. 120–180.

    Google Scholar 

  28. N. Cesa-Bianchi and G. Lugosi, Prediction and Playing Games, Cambridge University Press, 2006.

    Book  MATH  Google Scholar 

  29. ——, Prediction, Learning, and Games, Cambridge University Press, USA, 2006.

    Book  MATH  Google Scholar 

  30. G. Chalkiadakis, E. Elkind, and M. Wooldridge, Computational aspects of cooperative game theory, vol. 5, 10 2011.

    Google Scholar 

  31. A. Chivukula and W. Liu, Adversarial deep learning models with multiple adversaries, IEEE Transactions on Knowledge and Data Engineering, 31 (2019), pp. 1066–1079.

    Article  Google Scholar 

  32. A. S. Chivukula, X. Yang, W. Liu, T. Zhu, and W. Zhou, Game theoretical adversarial deep learning with variational adversaries, IEEE Transactions on Knowledge and Data Engineering, 33 (2021), pp. 3568–3581.

    Article  Google Scholar 

  33. S. Cohen, G. Dror, and E. Ruppin, Feature selection via coalitional game theory, Neural Comput., 19 (2007), p. 1939–1961.

    Article  MathSciNet  MATH  Google Scholar 

  34. A. Cotter, H. Jiang, and K. Sridharan, Two-player games for efficient non-convex constrained optimization, in ALT, vol. 98 of Proceedings of Machine Learning Research, PMLR, 2019, pp. 300–332.

    Google Scholar 

  35. G. Cybenko, S. Jajodia, M. P. Wellman, and P. Liu, Adversarial and uncertain reasoning for adaptive cyber defense: Building the scientific foundation, in ICISS, vol. 8880 of Lecture Notes in Computer Science, Springer, 2014, pp. 1–8.

    Google Scholar 

  36. N. Dalvi, P. Domingos, Mausam, S. Sanghai, and D. Verma, Adversarial classification, in Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’04, New York, NY, USA, 2004, ACM, pp. 99–108.

    Google Scholar 

  37. P. Dasgupta and J. B. Collins, A survey of game theoretic approaches for adversarial machine learning in cybersecurity tasks, AI Mag., 40 (2019), pp. 31–43.

    Google Scholar 

  38. S. De Silva, J. Kim, and R. Raich, Cost aware adversarial learning, in ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, pp. 3587–3591.

    Google Scholar 

  39. K. Deb and D. Saxena, On finding pareto-optimal solutions through dimensionality reduction for certain large-dimensional multi-objective optimization problems, IEEE Congress on Evolutionary Computation, (2005).

    Google Scholar 

  40. J. Dianetti and G. Ferrari, Nonzero-sum submodular monotone-follower games: Existence and approximation of nash equilibria, SIAM J. Control. Optim., 58 (2020), pp. 1257–1288.

    Article  MathSciNet  MATH  Google Scholar 

  41. P. Domingos, A unified bias-variance decomposition and its applications, in In Proc. 17th International Conf. on Machine Learning, Morgan Kaufmann, 2000, pp. 231–238.

    Google Scholar 

  42. L. Dritsoula, P. Loiseau, and J. Musacchio, A game-theoretical approach for finding optimal strategies in an intruder classification game, in CDC, IEEE, 2012, pp. 7744–7751.

    Google Scholar 

  43. A. Fawzi, O. Fawzi, and P. Frossard, Analysis of classifiers’ robustness to adversarial perturbations, Mach. Learn., 107 (2018), pp. 481–508.

    Article  MathSciNet  MATH  Google Scholar 

  44. ——, Knowledge discovery and data mining: Towards a unifying framework, in Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, KDD’96, AAAI Press, 1996, p. 82–88.

    Google Scholar 

  45. K. Ferguson-Walter, S. Fugate, J. Mauger, and M. Major, Game theory for adaptive defensive cyber deception, in Proceedings of the 6th Annual Symposium on Hot Topics in the Science of Security, HotSoS ’19, New York, NY, USA, 2019, Association for Computing Machinery.

    Google Scholar 

  46. S. Ficici, O. Melnik, and J. Pollack, A game-theoretic and dynamical-systems analysis of selection methods in coevolution, IEEE Transactions on Evolutionary Computation, 9 (2005), pp. 580–602.

    Article  Google Scholar 

  47. S. G. Ficici, A game-theoretic investigation of selection methods in two-population coevolution, in Proceedings of the 8th Annual Conference on Genetic and Evolutionary Computation, GECCO ’06, New York, NY, USA, 2006, Association for Computing Machinery.

    Google Scholar 

  48. S. G. Ficici and J. B. Pollack, A game-theoretic approach to the simple coevolutionary algorithm, in PPSN, vol. 1917 of Lecture Notes in Computer Science, Springer, 2000, pp. 467–476.

    Google Scholar 

  49. D. Fogel, An introduction to simulated evolutionary optimization, IEEE Transactions on Neural Networks, 5 (1994), pp. 3–14.

    Article  Google Scholar 

  50. B. Franci and S. Grammatico, A game-theoretic approach for generative adversarial networks, in CDC, IEEE, 2020, pp. 1646–1651.

    Google Scholar 

  51. G. Freiling, G. Jank, and S. R. Lee, Existence and uniqueness of open-loop stackelberg equilibria in linear-quadratic differential games, J. Optim. Theory Appl., 110 (2001), p. 515–544.

    Article  MathSciNet  MATH  Google Scholar 

  52. A. A. Freitas, A review of evolutionary algorithms for data mining, in Data Mining and Knowledge Discovery Handbook, Springer, 2010, pp. 371–400.

    Google Scholar 

  53. Y. Freund and R. E. Schapire, Game theory, on-line prediction and boosting, in Proceedings of the Ninth Annual Conference on Computational Learning Theory, COLT ’96, New York, NY, USA, 1996, Association for Computing Machinery, p. 325–332.

    Google Scholar 

  54. S. R. L. G. Freiling, G. Jank, Existence and uniqueness of open-loop stackelberg equilibria in linear-quadratic differential games, Journal of Optimization Theory and Applications, 110 (2001), pp. 515–544.

    Article  MathSciNet  MATH  Google Scholar 

  55. D. Garg, S. Sellamanickam, and S. Shevade, A game theoretic approach for feature clustering and its application to feature selection, 05 2011, pp. 13–25.

    Google Scholar 

  56. X. Ge, H. Ding, H. Rabitz, and R.-B. Wu, Robust quantum control in games: An adversarial learning approach, Phys. Rev. A, 101 (2020), p. 052317.

    Article  MathSciNet  Google Scholar 

  57. A. Globerson and S. Roweis, Nightmare at test time: Robust learning by feature deletion, in Proceedings of the 23rd International Conference on Machine Learning, ICML ’06, New York, NY, USA, 2006, ACM, pp. 353–360.

    Google Scholar 

  58. S. Gore and V. Govindaraju, Feature selection using cooperative game theory and relief algorithm, in Knowledge, Information and Creativity Support Systems: Recent Trends, Advances and Solutions - Selected Papers from KICSS’2013 - 8th International Conference on Knowledge, Information, and Creativity Support Systems, November 7-9, 2013, Kraków, Poland, A. M. J. Skulimowski and J. Kacprzyk, eds., vol. 364 of Advances in Intelligent Systems and Computing, Springer, 2013, pp. 401–412.

    Google Scholar 

  59. P. D. Grunwald and A. P. Dawid, Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory, The Annals of Statistics, 32 (2004), pp. 1367–1433.

    Article  MathSciNet  MATH  Google Scholar 

  60. J. Halpern, Computer science and game theory: A brief survey, Palgrave Dictionary of Economics, (2007).

    Google Scholar 

  61. S. N. Hamilton and W. L. Miller, The role of game theory in information warfare, 2002.

    Google Scholar 

  62. S. Hart and A. Mas-Colell, A general class of adaptive strategies., J. Econ. Theory, 98 (2001), pp. 26–54.

    Article  MathSciNet  MATH  Google Scholar 

  63. E. Hazan, K. Singh, and C. Zhang, Efficient regret minimization in non-convex games, in Proceedings of the 34th International Conference on Machine Learning - Volume 70, ICML’17, JMLR.org, 2017.

    Google Scholar 

  64. D. He, W. Chen, L. Wang, and T.-Y. Liu, A game- heoretic machine learning approach for revenue maximization in sponsored search, in Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence, IJCAI ’13, AAAI Press, 2013.

    Google Scholar 

  65. D. Henderson, S. Jacobson, and A. Johnson, The Theory and Practice of Simulated Annealing, 04 2006, pp. 287–319.

    Google Scholar 

  66. J. Herbert and J. Yao, A game-theoretic approach to competitive learning in self-organizing maps, vol. 3610, 08 2005, pp. 129–138.

    Google Scholar 

  67. T. Hinrichs and K. D. Forbus, Transfer learning through analogy in games, AI Magazine, 32 (2011), p. 70.

    Article  Google Scholar 

  68. L. Huang and Q. Zhu, A dynamic games approach to proactive defense strategies against advanced persistent threats in cyber-physical systems, Computers & Security, 89 (2019), p. 101660.

    Article  Google Scholar 

  69. Y. Huang, J. Chen, L. Huang, and Q. Zhu, Dynamic games for secure and resilient control system design, National Science Review, 7 (2020), pp. 1125–1141.

    Article  Google Scholar 

  70. R. Jia, I. C. Konstantakopoulos, B. Li, and C. Spanos, Poisoning attacks on data-driven utility learning in games, in 2018 Annual American Control Conference (ACC), 2018, pp. 5774–5780.

    Google Scholar 

  71. N. D. Johnson and A. A. Mislin, Trust games: A meta-analysis, Journal of Economic Psychology, 32 (2011), pp. 865–889.

    Article  Google Scholar 

  72. P. R. Jordan, L. J. Schvartzman, and M. P. Wellman, Strategy exploration in empirical games, in AAMAS, IFAAMAS, 2010, pp. 1131–1138.

    Google Scholar 

  73. M. Kantarcioglu, B. **, and C. Clifton, A game theoretic framework for adversarial learning, in Proceedings of the 9th Annual Information Security Symposium, CERIAS ’08, West Lafayette, IN, 2008, CERIAS - Purdue University.

    Google Scholar 

  74. M. Kantarcıoğlu, B. **, and C. Clifton, Classifier evaluation and attribute selection against active adversaries, Data Mining and Knowledge Discovery, 22 (2011), pp. 291–335.

    Article  MathSciNet  MATH  Google Scholar 

  75. M. Kantarcioglu, B. **, and C. Clifton, Classifier evaluation and attribute selection against active adversaries, Data Min. Knowl. Discov., 22 (2011), pp. 291–335.

    Article  MathSciNet  MATH  Google Scholar 

  76. J. Kleinberg, C. Papadimitriou, and P. Raghavan, A microeconomic view of data mining, 1998.

    Google Scholar 

  77. A. Kulkarni, S. Srivastava, and S. Kambhampati, A unified framework for planning in adversarial and cooperative environments, in AAAI, AAAI Press, 2019, pp. 2479–2487.

    Google Scholar 

  78. G. R. Lanckriet, L. E. Ghaoui, C. Bhattacharyya, and M. I. Jordan, A robust minimax approach to classification, J. Mach. Learn. Res., 3 (2003).

    Google Scholar 

  79. K. Leyton-Brown and Y. Shoham, vol. 2, 2008.

    Google Scholar 

  80. G. L’Huillier, R. Weber, and N. Figueroa, Online phishing classification using adversarial data mining and signaling games, in Proceedings of the ACM SIGKDD Workshop on CyberSecurity and Intelligence Informatics, CSI-KDD ’09, New York, NY, USA, 2009, Association for Computing Machinery.

    Google Scholar 

  81. B. Li and Y. Vorobeychik, Feature cross-substitution in adversarial classification, in Advances in Neural Information Processing Systems 27, Z. Ghahramani, M. Welling, C. Cortes, N. D. Lawrence, and K. Q. Weinberger, eds., Curran Associates, Inc., 2014, pp. 2087–2095.

    Google Scholar 

  82. ——, Scalable Optimization of Randomized Operational Decisions in Adversarial Classification Settings, in Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics, G. Lebanon and S. V. N. Vishwanathan, eds., vol. 38 of Proceedings of Machine Learning Research, San Diego, California, USA, 09–12 May 2015, PMLR, pp. 599–607.

    Google Scholar 

  83. C. Li, H. Farkhoor, R. Liu, and J. Yosinski, Measuring the intrinsic dimension of objective landscapes, in International Conference on Learning Representations, 2018.

    Google Scholar 

  84. H. Liaghati, T. Mazzuchi, and S. Sarkani, Utilizing a maximin optimization approach to maximize system resiliency, Systems Engineering, 24 (2021).

    Google Scholar 

  85. X. Liang and Y. **ao, Game theory for network security, IEEE Communications Surveys Tutorials, 15 (2013), pp. 472–486.

    Article  Google Scholar 

  86. M. Lippi, Statistical relational learning for game theory, IEEE Transactions on Computational Intelligence and AI in Games, 8 (2015), pp. 1–1.

    Google Scholar 

  87. Q. Liu, P. Li, W. Zhao, W. Cai, S. Yu, and V. C. M. Leung, A survey on security threats and defensive techniques of machine learning: A data driven view, IEEE Access, 6 (2018), pp. 12103–12117.

    Article  Google Scholar 

  88. W. Liu and S. Chawla, A game theoretical model for adversarial learning, in 2009 IEEE International Conference on Data Mining Workshops, 2009, pp. 25–30.

    Google Scholar 

  89. ——, Mining adversarial patterns via regularized loss minimization, Machine Learning, 81 (2010), pp. 69–83.

    Google Scholar 

  90. ——, Mining adversarial patterns via regularized loss minimization, Mach. Learn., 81 (2010), pp. 69–83.

    Google Scholar 

  91. W. Liu, S. Chawla, J. Bailey, C. Leckie, and K. Ramamohanarao, AI 2012: Advances in Artificial Intelligence: 25th Australasian Joint Conference, Sydney, Australia, December 4-7, 2012. Proceedings, Springer Berlin Heidelberg, Berlin, Heidelberg, 2012, ch. An Efficient Adversarial Learning Strategy for Constructing Robust Classification Boundaries, pp. 649–660.

    Google Scholar 

  92. S. Lloyd and C. Weedbrook, Quantum generative adversarial learning, Phys. Rev. Lett., 121 (2018), p. 040502.

    Article  MathSciNet  Google Scholar 

  93. D. Lowd and C. Meek, Adversarial learning, in Proceedings of the Eleventh ACM SIGKDD International Conference on Knowledge Discovery in Data Mining, KDD ’05, New York, NY, USA, 2005, ACM, pp. 641–647.

    Google Scholar 

  94. O. Maimon and L. Rokach, Decomposition Methodology for Knowledge Discovery and Data Mining - Theory and Applications, vol. 61 of Series in Machine Perception and Artificial Intelligence, WorldScientific, 2005.

    Google Scholar 

  95. M. H. Manshaei, Q. Zhu, T. Alpcan, T. Bacşar, and J.-P. Hubaux, Game theory meets network security and privacy, ACM Comput. Surv., 45 (2013).

    Google Scholar 

  96. O. Martin and S. Otto, Combining simulated annealing with local search heuristics, Annals of Operations Research, 63 (1999).

    Google Scholar 

  97. J. V. Medanic and D. G. Radojevic, Multilevel stackelberg strategies in linear-quadratic systems, Journal of Optimization Theory and Applications, 24 (1978), pp. 485–497.

    Article  MathSciNet  MATH  Google Scholar 

  98. B. Miller, A. Kantchelian, S. Afroz, R. Bachwani, E. Dauber, L. Huang, M. C. Tschantz, A. D. Joseph, and J. Tygar, Adversarial active learning, in Proceedings of the 2014 Workshop on Artificial Intelligent and Security Workshop, AISec ’14, New York, NY, USA, 2014, Association for Computing Machinery.

    Google Scholar 

  99. D. J. Miller, X. Hu, Z. Qiu, and G. Kesidis, Adversarial learning: A critical review and active learning study, in MLSP, IEEE, 2017, pp. 1–6.

    Google Scholar 

  100. R. Motwani and P. Raghavan, Randomized Algorithms, Cambridge University Press, Cambridge; NY, 1995.

    Google Scholar 

  101. A. Nagurney, P. Daniele, and S. Shukla, A supply chain network game theory model of cybersecurity investments with nonlinear budget constraints, Ann. Oper. Res., 248 (2017), pp. 405–427.

    Article  MathSciNet  MATH  Google Scholar 

  102. Y. Narahari, Game Theory and Mechanism Design, WORLD SCIENTIFIC / INDIAN INST OF SCIENCE, INDIA, 2014.

    Google Scholar 

  103. Y. Narahari, D. Garg, R. Narayanam, and H. Prakash, Game Theoretic Problems in Network Economics and Mechanism Design Solutions, Springer Publishing Company, Incorporated, 1 ed., 2009.

    MATH  Google Scholar 

  104. R. Narayanam and Y. Narahari, A shapley value-based approach to discover influential nodes in social networks, IEEE Transactions on Automation Science and Engineering, 8 (2011), pp. 130–147.

    Article  Google Scholar 

  105. R. Narayanam and Y. Narahari, A game theory inspired, decentralized, local information based algorithm for community detection in social graphs, in ICPR, IEEE Computer Society, 2012, pp. 1072–1075.

    Google Scholar 

  106. J. Nash, Non-cooperative games, Annals of Mathematics, 54 (1951), pp. 286–295.

    Article  MathSciNet  MATH  Google Scholar 

  107. J. F. Nash, Equilibrium points in n-person games., Proceedings of the National Academy of Sciences of the United States of America, 36 1 (1950), pp. 48–9.

    Article  MathSciNet  MATH  Google Scholar 

  108. B. Nelson, B. Rubinstein, L. Huang, A. Joseph, S. Lau, S. Lee, S. Rao, A. Tran, and D. Tygar, Near-optimal evasion of convex-inducing classifiers, in Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, Y. W. Teh and M. Titterington, eds., vol. 9 of Proceedings of Machine Learning Research, Chia Laguna Resort, Sardinia, Italy, 13–15 May 2010, PMLR, pp. 549–556.

    Google Scholar 

  109. T. Nguyen, M. P. Wellman, and S. P. Singh, A stackelberg game model for botnet data exfiltration, in GameSec, vol. 10575 of Lecture Notes in Computer Science, Springer, 2017, pp. 151–170.

    Google Scholar 

  110. T. H. Nguyen, Y. Wang, A. Sinha, and M. P. Wellman, Deception in finitely repeated security games, in AAAI, AAAI Press, 2019, pp. 2133–2140.

    Google Scholar 

  111. T. H. Nguyen, M. Wright, M. P. Wellman, and S. P. Singh, Multistage attack graph security games: Heuristic strategies, with empirical game-theoretic analysis, Secur. Commun. Networks, 2018 (2018), pp. 2864873:1–2864873:28.

    Google Scholar 

  112. A. Nisioti, G. Loukas, A. Laszka, and E. Panaousis, Data-driven decision support for optimizing cyber forensic investigations, IEEE Trans. Inf. Forensics Secur., 16 (2021), pp. 2397–2412.

    Article  Google Scholar 

  113. G. M. D. Nunzio, M. Maistro, and D. C. Zilio, Gamification for machine learning: The classification game, in GamifIR@SIGIR, 2016.

    Google Scholar 

  114. F. A. Oliehoek, E. D. de Jong, and N. Vlassis, The parallel nash memory for asymmetric games, in Proceedings of the 8th Annual Conference on Genetic and Evolutionary Computation, GECCO ’06, New York, NY, USA, 2006, Association for Computing Machinery.

    Google Scholar 

  115. F. A. Oliehoek, R. Savani, J. Gallego-Posada, E. van der Pol, E. D. de Jong, and R. Gross, Gangs: Generative adversarial network games, CoRR, abs/1712.00679 (2017).

    Google Scholar 

  116. U. O’Reilly and E. Hemberg, An artificial coevolutionary framework for adversarial ai, in AAAI Fall Symposium: ALEC, vol. 2269 of CEUR Workshop Proceedings, CEUR-WS.org, 2018, pp. 50–55.

    Google Scholar 

  117. M. J. Osborne and A. Rubinstein, A Course in Game Theory, vol. 1 of MIT Press Books, The MIT Press, 1994.

    Google Scholar 

  118. H. Otrok, B. Zhu, H. Yahyaoui, and P. Bhattacharya, An intrusion detection game theoretical model, Information Security Journal: A Global Perspective, 18 (2009), pp. 199–212.

    Google Scholar 

  119. N. Papernot, P. McDaniel, A. Sinha, and M. P. Wellman, Sok: Security and privacy in machine learning, in 2018 IEEE European Symposium on Security and Privacy (EuroS P), April 2018, pp. 399–414.

    Google Scholar 

  120. J. Pawlick, E. Colbert, and Q. Zhu, A game-theoretic taxonomy and survey of defensive deception for cybersecurity and privacy, ACM Comput. Surv., 52 (2019).

    Google Scholar 

  121. A. Prakash and M. P. Wellman, Empirical game-theoretic analysis for moving target defense, in MTD@CCS, ACM, 2015, pp. 57–65.

    Google Scholar 

  122. S. Rajasekaran, On simulated annealing and nested annealing, Journal of Global Optimization, 16 (2000), pp. 43–56.

    Article  MathSciNet  MATH  Google Scholar 

  123. A. Rakhlin and K. Sridharan, Optimization, learning, and games with predictable sequences, in NIPS, 2013, pp. 3066–3074.

    Google Scholar 

  124. D. Ram, T. Sreenivas, and K. Subramaniam, Parallel simulated annealing algorithms, J. Parallel Distrib. Comput., 37 (1996), p. 207–212.

    Article  Google Scholar 

  125. S. Rass, S. Konig, and S. Schauer, Defending against advanced persistent threats using game-theory, PLOS ONE, 12 (2017), pp. 1–43.

    Article  Google Scholar 

  126. L. Ratliff, S. Burden, and S. Sastry, Characterization and computation of local nash equilibria in continuous games, 10 2013, pp. 917–924.

    Google Scholar 

  127. I. Rezek, D. S. Leslie, S. Reece, S. J. Roberts, A. Rogers, R. K. Dash, and N. R. Jennings, On similarities between inference in game theory and machine learning, J. Artif. Int. Res., 33 (2008), p. 259–283.

    MathSciNet  MATH  Google Scholar 

  128. D. Rios Insua, R. Naveiro, and V. Gallego, Perspectives on adversarial classification, Mathematics, 8 (2020).

    Google Scholar 

  129. T. Roeder and F. B. Schneider, Proactive obfuscation, ACM Trans. Comput. Syst., 28 (2010), pp. 4:1–4:54.

    Google Scholar 

  130. J. Romero and A. Aspuru-Guzik, Variational quantum generators: Generative adversarial quantum machine learning for continuous distributions, Advanced Quantum Technologies, 4 (2020), p. 2000003.

    Article  Google Scholar 

  131. S. Roy, C. Ellis, S. Shiva, D. Dasgupta, V. Shandilya, and Q. Wu, A survey of game theory as applied to network security, in 2010 43rd Hawaii International Conference on System Sciences, 2010, pp. 1–10.

    Google Scholar 

  132. A. Schlenker, O. Thakoor, H. Xu, F. Fang, M. Tambe, L. Tran-Thanh, P. Vayanos, and Y. Vorobeychik, Deceiving cyber adversaries: A game theoretic approach, in Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems, AAMAS ’18, Richland, SC, 2018, International Foundation for Autonomous Agents and Multiagent Systems, p. 892–900.

    Google Scholar 

  133. L. Schmidt, S. Santurkar, D. Tsipras, K. Talwar, and A. Madry, Adversarially robust generalization requires more data, in Proceedings of the 32nd International Conference on Neural Information Processing Systems, NIPS’18, Red Hook, NY, USA, 2018, Curran Associates Inc., p. 5019–5031.

    Google Scholar 

  134. D. Schuurmans and M. A. Zinkevich, Deep learning games, in Advances in Neural Information Processing Systems, D. Lee, M. Sugiyama, U. Luxburg, I. Guyon, and R. Garnett, eds., vol. 29, Curran Associates, Inc., 2016.

    Google Scholar 

  135. G. Scutari, D. P. Palomar, F. Facchinei, and J.-s. Pang, Convex optimization, game theory, and variational inequality theory, IEEE Signal Processing Magazine, 27 (2010), pp. 35–49.

    Article  Google Scholar 

  136. H. Shah, V. Kakkad, R. Patel, and N. Doshi, A survey on game theoretic approaches for privacy preservation in data mining and network security, Procedia Computer Science, 155 (2019), pp. 686–691. The 16th International Conference on Mobile Systems and Pervasive Computing (MobiSPC 2019),The 14th International Conference on Future Networks and Communications (FNC-2019),The 9th International Conference on Sustainable Energy Information Technology.

    Google Scholar 

  137. M. Simaan and J. B. Cruz, Jr., On the stackelberg strategy in nonzero-sum games, J. Optim. Theory Appl., 11 (1973), pp. 533–555.

    Article  MathSciNet  MATH  Google Scholar 

  138. ——, An efficient explanation of individual classifications using game theory, J. Mach. Learn. Res., 11 (2010).

    Google Scholar 

  139. B. Suman and P. Kumar, A survey of simulated annealing as a tool for single and multiobjective optimization, Journal of the Operational Research Society, 57 (2006), pp. 1143–1160.

    Article  MATH  Google Scholar 

  140. X. Sun, Y. Liu, J. Li, J. Zhu, H. Chen, and X. Liu, Feature evaluation and selection with cooperative game theory, Pattern Recogn., 45 (2012), p. 2992–3002.

    Article  Google Scholar 

  141. X. Sun, Y. Liu, J. Li, J. Zhu, X. Liu, and H. Chen, Using cooperative game theory to optimize the feature selection problem, Neurocomput., 97 (2012).

    Google Scholar 

  142. V. Syrgkanis, A. Agarwal, H. Luo, and R. E. Schapire, Fast convergence of regularized learning in games, in Advances in Neural Information Processing Systems, C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, and R. Garnett, eds., vol. 28, Curran Associates, Inc., 2015.

    Google Scholar 

  143. L. Tong, S. Yu, S. Alfeld, and yevgeniy vorobeychik, Adversarial regression with multiple learners, in Proceedings of the 35th International Conference on Machine Learning, J. Dy and A. Krause, eds., vol. 80 of Proceedings of Machine Learning Research, PMLR, 10–15 Jul 2018, pp. 4946–4954.

    Google Scholar 

  144. E. Triantaphyllou, Data Mining and Knowledge Discovery via Logic-Based Methods, no. 978-1-4419-1630-3 in Springer Optimization and Its Applications, Springer, September 2010.

    Google Scholar 

  145. D. Tsipras, S. Santurkar, L. Engstrom, A. Turner, and A. Madry, Robustness may be at odds with accuracy, in ICLR (Poster), OpenReview.net, 2019.

    Google Scholar 

  146. M. Ummels, Stochastic multiplayer games: theory and algorithms, PhD thesis, RWTH Aachen University, 2011.

    Google Scholar 

  147. Y. Vorobeychik, M. P. Wellman, and S. P. Singh, Learning payoff functions in infinite games, in IJCAI, Professional Book Center, 2005, pp. 977–982.

    Google Scholar 

  148. F. Wang, W. Liu, and S. Chawla, On sparse feature attacks in adversarial learning, in 2014 IEEE International Conference on Data Mining, Dec 2014, pp. 1013–1018.

    Google Scholar 

  149. X. Wang, C. Hoang, Y. Vorobeychik, and M. P. Wellman, Spoofing the limit order book: A strategic agent-based analysis, Games, 12 (2021), p. 46.

    Article  MathSciNet  MATH  Google Scholar 

  150. Y. Wang, Integration of data mining with game theory, in Knowledge Enterprise: Intelligent Strategies in Product Design, Manufacturing, and Management, K. Wang, G. L. Kovacs, M. Wozny, and M. Fang, eds., Boston, MA, 2006, Springer US, pp. 275–280.

    Google Scholar 

  151. J. Webb, Game Theory: Decisions, Interaction and Evolution, 01 2007.

    Google Scholar 

  152. M. P. Wellman, Methods for empirical game-theoretic analysis, in AAAI, AAAI Press, 2006, pp. 1552–1556.

    Google Scholar 

  153. M. P. Wellman, L. Hong, and S. E. Page, The structure of signals: Causal interdependence models for games of incomplete information, in UAI, AUAI Press, 2011, pp. 727–735.

    Google Scholar 

  154. Q. Xu, K. Bello, and J. Honorio, A le cam type bound for adversarial learning and applications, in 2021 IEEE International Symposium on Information Theory (ISIT), 2021, pp. 1164–1169.

    Google Scholar 

  155. M. Xue, C. Yuan, H. Wu, Y. Zhang, and W. Liu, Machine learning security: Threats, countermeasures, and evaluations, IEEE Access, 8 (2020), pp. 74720–74742.

    Article  Google Scholar 

  156. O. Yair and T. Michaeli, Contrastive divergence learning is a time reversal adversarial game, in ICLR, OpenReview.net, 2021.

    Google Scholar 

  157. L. Yang, P. Li, Y. Zhang, X. Yang, Y. **ang, and W. Zhou, Effective repair strategy against advanced persistent threat: A differential game approach, IEEE Transactions on Information Forensics and Security, 14 (2019), pp. 1713–1728.

    Article  Google Scholar 

  158. D. Ye, T. Zhu, S. Shen, and W. Zhou, A differentially private game theoretic approach for deceiving cyber adversaries, IEEE Trans. Inf. Forensics Secur., 16 (2021), pp. 569–584.

    Article  Google Scholar 

  159. S. Ye, X. Lin, K. Xu, S. Liu, H. Cheng, J.-H. Lambrechts, H. Zhang, A. Zhou, K. Ma, and Y. Wang, Adversarial robustness vs. model compression, or both?, 2019 IEEE/CVF International Conference on Computer Vision (ICCV), (2019), pp. 111–120.

    Google Scholar 

  160. Z. Yin, F. Wang, W. Liu, and S. Chawla, Sparse feature attacks in adversarial learning, IEEE Transactions on Knowledge and Data Engineering, PP (2018).

    Google Scholar 

  161. ——, Sparse feature attacks in adversarial learning, IEEE Transactions on Knowledge and Data Engineering, 30 (2018), pp. 1164–1177.

    Article  Google Scholar 

  162. J. Zhang, Z. Zhan, Y. Lin, N. Chen, Y. Gong, J. Zhong, H. S. H. Chung, Y. Li, and Y. Shi, Evolutionary computation meets machine learning: A survey, IEEE Computational Intelligence Magazine, 6 (2011), pp. 68–75.

    Article  Google Scholar 

  163. L. Zhang, T. Zhu, P. **ong, W. Zhou, and P. S. Yu, More than privacy: Adopting differential privacy in game-theoretic mechanism design, ACM Comput. Surv., 54 (2021).

    Google Scholar 

  164. Y. Zhou and M. Kantarcioglu, Modeling adversarial learning as nested stackelberg games, in Advances in Knowledge Discovery and Data Mining, J. Bailey, L. Khan, T. Washio, G. Dobbie, J. Z. Huang, and R. Wang, eds., Cham, 2016, Springer International Publishing, pp. 350–362.

    Google Scholar 

  165. ——, Modeling adversarial learning as nested stackelberg games, in Proceedings, Part II, of the 20th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining - Volume 9652, PAKDD 2016, Berlin, Heidelberg, 2016, Springer-Verlag, p. 350–362.

    Google Scholar 

  166. Y. Zhou, M. Kantarcioglu, and B. **, A survey of game theoretic approach for adversarial machine learning, WIREs Data Mining and Knowledge Discovery, 9 (2019), p. e1259.

    Article  Google Scholar 

  167. ——, A survey of game theoretic approach for adversarial machine learning, Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, (2019).

    Book  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science & Information Systems, BITS Pilani Hyderabad Campus, Secunderabad, Hyderabad, Telangana, India

    Aneesh Sreevallabh Chivukula

  2. Computer Science, University of Technology Sydney, Sydney, NSW, Australia

    **nghao Yang, Bo Liu, Wei Liu & Wanlei Zhou

Authors
  1. Aneesh Sreevallabh Chivukula
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. **nghao Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Bo Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Wei Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Wanlei Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Sreevallabh Chivukula, A., Yang, X., Liu, B., Liu, W., Zhou, W. (2023). Game Theoretical Adversarial Deep Learning. In: Adversarial Machine Learning. Springer, Cham. https://doi.org/10.1007/978-3-030-99772-4_4

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-99772-4_4

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-99771-7

  • Online ISBN: 978-3-030-99772-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation