Large-scale strategic games and adversarial machine learning

Decision making in modern large-scale and complex systems such as communication networks, smart electricity grids, and cyber-physical systems motivate novel game-theoretic approaches. This paper investigates big strategic (non-cooperative) games where a finite number of individual players each have a large number of continuous decision variables and input data points. Such high-dimensional decision spaces and big data sets lead to computational challenges, relating to efforts in non-linear optimization scaling up to large systems of variables. In addition to these computational challenges, real-world players often have limited information about their preference parameters due to the prohibitive cost of identifying them or due to operating in dynamic online settings. The challenge of limited information is exacerbated in high dimensions and big data sets. Motivated by both computational and information limitations that constrain the direct solution of big strategic games, our investigation centers around reductions using linear transformations such as random projection methods and their effect on Nash equilibrium solutions. Specific analytical results are presented for quadratic games and approximations. In addition, an adversarial learning game is presented where random projection and sampling schemes are investigated.

[1]  Rong Yang,et al.  Scaling-up Security Games with Boundedly Rational Adversaries: A Cutting-plane Approach , 2013, IJCAI.

[2]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[3]  Blaine Nelson,et al.  The security of machine learning , 2010, Machine Learning.

[4]  Santosh S. Vempala,et al.  An algorithmic theory of learning: Robust concepts and random projection , 1999, Machine Learning.

[5]  W. B. Johnson,et al.  Extensions of Lipschitz mappings into Hilbert space , 1984 .

[6]  Wenke Lee,et al.  Evading network anomaly detection systems: formal reasoning and practical techniques , 2006, CCS '06.

[7]  Pedro M. Domingos,et al.  Adversarial classification , 2004, KDD.

[8]  Juliane Hahn,et al.  Security And Game Theory Algorithms Deployed Systems Lessons Learned , 2016 .

[9]  Cynthia Dwork,et al.  Calibrating Noise to Sensitivity in Private Data Analysis , 2006, TCC.

[10]  Shyhtsun Felix Wu,et al.  On Attacking Statistical Spam Filters , 2004, CEAS.

[11]  Volkan Cevher,et al.  Convex Optimization for Big Data: Scalable, randomized, and parallel algorithms for big data analytics , 2014, IEEE Signal Processing Magazine.

[12]  H. Vincent Poor,et al.  Mechanisms and Games for Dynamic Spectrum Allocation: Preface , 2013 .

[13]  James Newsome,et al.  Paragraph: Thwarting Signature Learning by Training Maliciously , 2006, RAID.

[14]  Tim Roughgarden,et al.  Algorithmic Game Theory , 2007 .

[15]  T. Başar,et al.  Dynamic Noncooperative Game Theory , 1982 .

[16]  Christopher Meek,et al.  Good Word Attacks on Statistical Spam Filters , 2005, CEAS.

[17]  Yehuda Lindell,et al.  Privacy Preserving Data Mining , 2000, Journal of Cryptology.

[18]  Tansu Alpcan,et al.  A Game-Theoretic Analysis of Wind Generation Variability on Electricity Markets , 2014, IEEE Transactions on Power Systems.

[19]  Quanyan Zhu,et al.  Game-Theoretic Methods for Robustness, Security, and Resilience of Cyberphysical Control Systems: Games-in-Games Principle for Optimal Cross-Layer Resilient Control Systems , 2015, IEEE Control Systems.

[20]  Marimuthu Palaniswami,et al.  Security Games for Risk Minimization in Automatic Generation Control , 2015, IEEE Transactions on Power Systems.

[21]  Leandro Soriano Marcolino,et al.  Give a Hard Problem to a Diverse Team: Exploring Large Action Spaces , 2014, AAAI.

[22]  Gábor Lugosi,et al.  Prediction, learning, and games , 2006 .

[23]  Tuomas Sandholm,et al.  Abstraction for Solving Large Incomplete-Information Games , 2015, AAAI.

[24]  Branislav Bosanský,et al.  Combining Compact Representation and Incremental Generation in Large Games with Sequential Strategies , 2015, AAAI.

[25]  Joe Michael Kniss,et al.  Satisficing the Masses: Applying Game Theory to Large-Scale, Democratic Decision Problems , 2009, 2009 International Conference on Computational Science and Engineering.

[26]  Nicolas Christin,et al.  Regret Minimizing Audits: A Learning-Theoretic Basis for Privacy Protection , 2011, 2011 IEEE 24th Computer Security Foundations Symposium.

[27]  Ling Huang,et al.  ANTIDOTE: understanding and defending against poisoning of anomaly detectors , 2009, IMC '09.

[28]  Cynthia Dwork,et al.  Calibrating Noise to Sensitivity in Private Data Analysis , 2016, J. Priv. Confidentiality.

[29]  Hamidou Tembine Nonasymptotic Mean-Field Games , 2014 .

[30]  Radford M. Neal Pattern Recognition and Machine Learning , 2007, Technometrics.

[31]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, CACM.

[32]  A. Atiya,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2005, IEEE Transactions on Neural Networks.

[33]  Benjamin Recht,et al.  Random Features for Large-Scale Kernel Machines , 2007, NIPS.

[34]  Walid Saad,et al.  Game-Theoretic Methods for the Smart Grid: An Overview of Microgrid Systems, Demand-Side Management, and Smart Grid Communications , 2012, IEEE Signal Processing Magazine.

[35]  Kaare Brandt Petersen,et al.  The Matrix Cookbook , 2006 .

[36]  Alain Haurie,et al.  On the relationship between Nash - Cournot and Wardrop equilibria , 1983, Networks.

[37]  Blaine Nelson,et al.  Exploiting Machine Learning to Subvert Your Spam Filter , 2008, LEET.

[38]  Tobias Scheffer,et al.  Nash Equilibria of Static Prediction Games , 2009, NIPS.

[39]  Tansu Alpcan,et al.  Network Security , 2010 .

[40]  Christos Boutsidis,et al.  Random Projections for Linear Support Vector Machines , 2012, TKDD.