2023

C

Generative Modelling of Stochastic Actions with Arbitrary Constraints in Reinforcement Learning By Changyu Chen, Ramesha Karunasena, Thanh Hong Nguyen, Arunesh Sinha, Pradeep Varakantham In NeurIPS-23: Proc. 37th Conference on Neural Information Processing Systems (NeurIPS), December 2023.

C

CounterNet: End-to-End Training of Prediction Aware Counterfactual Explanations By Hangzhi Guo, Thanh H. Nguyen, Amulya Yadav In KDD-23: Proc. 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), August 2023.

C

Building a Personalized Messaging System for Health Intervention in Underprivileged Regions Using Reinforcement Learning By Sarah Kinsey, Jack Wolf, Nalini Saligram, Varun Ramesan, Meeta Walavalkar, Nidhi Jaswal, Sandhya Ramalingam, Arunesh Sinha, Thanh H. Nguyen. In IJCAI-23: Proc. the 32th International Joint Conference on Artificial Intelligence (IJCAI), AI for Good Track, August 2023.

C

Imitating Opponent to Win: Adversarial Policy Imitation Learning in Two-player Competitive Games [PDF] By The Viet Bui, Tien Mai, Thanh H. Nguyen In AAMAS-23: Proc. the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS), May 2023.

C

Beyond NaN: Resiliency of Optimization Layers in the Face of Instability [PDF] By Wai Tuck Wong, Sarah Kinsey, Ramesha Karunasena, Thanh H. Nguyen, Arunesh Sinha. In AAAI-23: Proc. the 37th AAAI Conference on Artificial Intelligence (AAAI), February 2023.

C

Behavioral Learning in Security Games: Threat of Multi-Step Manipulative Attacks [PDF] By Thanh H. Nguyen, Arunesh Sinha. In AAAI-23: Proc. the 37th AAAI Conference on Artificial Intelligence (AAAI), February 2023.

2022

J

A Complete Analysis on the Risk of Using Quantal Response: When Attacker Maliciously Changes Behavior under Uncertainty. [PDF] By Thanh H. Nguyen, Amulya Yadav. In Games-22: the Games Journal, 2022, 13(6), 81; https://doi.org/10.3390/g13060081

C

Information Design for Multiple Independent and Self-Interested Defenders: Work Less, Pay Off More [PDF] By Chenghan Zhou, Andrew Spivey, Haifeng Xu, Thanh H. Nguyen. In UAI-22: Proc. 38th Conference on Uncertainty in Artificial Intelligence (UAI), August 2022.

C

Algorithmic Information Design in Multi-Player Games: Possibilities and Limits in Singleton Congestion [PDF] By Chenghan Zhou, Thanh H. Nguyen, and Haifeng Xu. In EC-22: Proc. 23th ACM Conference on Economics and Computation, July 2022.

C

When Can the Defender Effectively Deceive Attackers in Security Games? [PDF] By Thanh H. Nguyen, Haifeng Xu. In AAAI-22: Proc. the 36th AAAI Conference on Artificial Intelligence (AAAI), February 2022.

C

An Exploration of Poisoning Attacks on Data-based Decision Making [PDF] By Sarah Kinsey, Wong Wei Tuck, Arunesh Sinha, and Thanh H. Nguyen. In GameSec-22: Proc. of the 13th Conference on Decision and Game Theory for Security (GameSec), October 2022.

C

The Risk of Attacker Behavioral Learning: Can Attacker Fool Defender under Uncertainty? [PDF] By Thanh H. Nguyen, Amulya Yadav. In GameSec-22: Proc. of the 13th Conference on Decision and Game Theory for Security (GameSec), October 2022.

W

Poisoning Attacks on Data-based Decision Making: A Preliminary Study. By Ryan Butler, Wong Wai Tuck, Arunesh Sinha, Thanh H. Nguyen. In AASG-22: 3rd Autonomous Agents for Social Good (AASG) held at the 21st International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), May 2022.

W

Algorithmic Information Design for Singleton Congestion Games. By Chenghan Zhou, Thanh H. Nguyen, Haifeng Xu. In GCLR-22: 2nd Workshop on Graphs and More Complex Structures for Learning and Reasoning (GCLR) held at the 36th AAAI Conference on Artificial Intelligence (AAAI), February 2022.

2021

C

Countering Attacker Data Manipulation in Security Games. [PDF] By Ryan Butler, Arunesh Sinha, Thanh H. Nguyen. In GameSec-21: Proc. of the 11th Conference on Decision and Game Theory for Security (GameSec), October 2021.

W

CounterNet: End-to-End Training of Counterfactual Aware Predictions. [PDF] By Hangzhi Guo, Thanh H. Nguyen, Amulya Yadav. In Recourse-21: ICML Workshop on Algorithmic Recourse held at the Thirty-eighth International Conference on Machine Learning (ICML), July 2021. Runner-Up of the Best Paper Award

W

Sequential Manipulative Attacks in Security Games. [PDF] By Thanh H. Nguyen, Arunesh Sinha. In AASG-21: Workshop on Autonomous Agents for Social Good (AASG) held at the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), May 2021.

2020

B

Be Careful When Learning Against Adversaries: Imitative Attacker Deception in Stackelberg Security Games. [PDF] By Haifeng Xu, Thanh H. Nguyen. In Adversary-Aware Learning Techniques and Trends in Cybersecurity. Springer, 2020.

C

Using One-Sided Partially Observable Stochastic Games for Solving Zero-Sum Security Games with Sequential Attacks. [PDF] By Petr Tomášek, Branislav Bosansky, Thanh H. Nguyen. In GameSec-20: Proc. of the 11th Conference on Decision and Game Theory for Security (GameSec), November 2020.

C

Partial Adversarial Behavior Deception in Security Games. [PDF] By Thanh H. Nguyen, Arunesh Sinha, He He. In IJCAI-20: Proc. the 29th International Joint Conference on Artificial Intelligence (IJCAI), July 2020 (Acceptance rate: 12.6%).

C

Decoding the Imitation Security Game: Handling Attacker Imitative Behavior Deception. [PDF] By Thanh H. Nguyen, Nam Vu, Amulya Yadav, Uy Nguyen. In ECAI-20: Proc. of the 24th European Conference on Artificial Intelligence (ECAI), September 2020.

C

Tackling Imitative Attacker Deception in Repeated Bayesian Stackelberg Security Games. [PDF] By Thanh H. Nguyen, Andrew Butler, Haifeng Xu. In ECAI-20: Proc. of the 24th European Conference on Artificial Intelligence (ECAI), September 2020.

C

Application-Layer DDoS Defense with Reinforcement Learning. [PDF] By Yebo Feng, Jun Li, Thanh H. Nguyen. In IWQoS-20: Proc. of the IEEE/ACM 28th International Symposium on Quality of Service (IWQoS), June 2020.

W

Intelligent Tutoring Strategies for Students with Autism Spectrum Disorder: A Reinforcement Learning Approach. [PDF] By Stephanie Milani, Amulya Yadav, Fei Fang, Thanh H. Nguyen, Zhou Fan and Saurabh Gulati. In AI4EDU-20: Workshop on Artifical Intelligence for Education held at the 34nd AAAI Conference on Artificial Intelligence (AAAI), February 2020.

2019

B

Adaptive Cyber Defenses for Botnet Detection and Mitigation. [PDF] By Massimiliano Albanese, Sushil Jajodia, Sridhar Venkatesan, George Cybenko, Thanh H. Nguyen. In Adversarial and Uncertain Reasoning for Adaptive Cyber Defense. Springer, 2019.

B

Empirical Game-Theoretic Methods for Adaptive Cyber-Defense. [PDF] By Michael P. Wellman, Thanh H. Nguyen, Mason Wright. In Adversarial and Uncertain Reasoning for Adaptive Cyber Defense. Springer, 2019.

C

Tackling Sequential Attacks in Security Games. [PDF] By Thanh H. Nguyen, Amulya Yadav, Branislav Bosansky, Yu Liang. In GameSec-19: Proc. of the 10th Conference on Decision and Game Theory for Security (GameSec), November 2019.

C

Learning to Signal in the Goldilocks Zone: Improving Adversary Compliance in Security Games. [PDF] By Sarah Cooney, Kai Wang, Elizabeth Bondi, Thanh H. Nguyen, Phebe Vayanos, Hailey Winetrobe, Edward A. Cranford, Cleotilde Gonzalez, Christian Lebiere, Milind Tambe. In ECMLPKDD-19: Proc. the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD), September 2019 (Acceptance rate: 17.7%).

C

Imitative Attacker Deception in Stackelberg Security Games. [PDF] By Thanh H. Nguyen, Haifeng Xu. In IJCAI-19: Proc. the 28th International Joint Conference on Artificial Intelligence (IJCAI), August 2019 (Acceptance rate: 17.9%).

C

Warning Time: Optimizing Strategic Signaling for Security Against Boundedly Rational Adversaries (Extended Abstract). [PDF] By Sarah Cooney, Phebe Vayanos, Thanh H. Nguyen, Cleotilde Gonzalez, Christian Lebiere, Edward A. Cranford, Milind Tambe. In AAMAS-19: Proc. the 18th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), May 2019.

C

Deception in Finitely Repeated Security Games. [PDF] By Thanh H. Nguyen, Yongzhao Wang, Arunesh Sinha, Michael P. Wellman. In AAAI-19: Proc. the 33rd AAAI Conference on Artificial Intelligence (AAAI), January 2019 (Acceptance rate: 16.2%).

2018

J

Multi-Stage Attack Graph Security Games: Heuristic Strategies, with Empirical Game-Theoretic Analysis. [PDF] By Thanh H. Nguyen, Mason Wright, Michael P. Wellman, Satinder Singh. In SCN-18: Proc. of the Journal of the Security and Communication Networks, 2018.

W

Deceitful Attacks in Security Games. [PDF] By Thanh H. Nguyen, Michael P. Wellman, Arunesh Sinha. In AICS-18: Workshop on Artificial Intelligence for Cyber Security held at the 32nd AAAI Conference on Artificial Intelligence (AAAI), February 2018.

2017

M

PAWS – A Deployed Game-Theoretic Application to Combat Poaching. [PDF] By Fei Fang, Thanh H. Nguyen, Rob Pickles, Wai Y. Lam, Gopalasamy R. Clements, Bo An, Amandeep Singh, Brian C. Schwedock, Milind Tambe, Andrew Lemieux. In AI-Magazine-17: AI Magazine 2017, 38(1):23-36. DOI: https://doi.org/10.1609/aimag.v38i1.2710.

M

Keeping it Real: Using Real-World Problems to Teach AI to Diverse Audiences. [PDF] By Nicole Sintov, Debarun Kar, Thanh H. Nguyen, Fei Fang, Kevin Hoffman, Arnaud Lyet, Milind Tambe. In AI-Magazine-17: AI Magazine 2017, 38 (2):35-47. DOI: https://doi.org/10.1609/aimag.v38i2.2733.

M

Predicting Poaching for Wildlife Protection. [PDF] By Fei Fang, Thanh H. Nguyen, Arunesh Sinha, Shahrzad Gholami, Andrew Plumptre, Lucas Joppa, Milind Tambe, Margaret Driciru, Fred Wanyama, Aggrey Rwetsiba, Rob Critchlow, Colin Beale. In IBM Tech. Magazine Article-17: IBM Journal of Research and Development 2017, 61(6):3:1-3:12. DOI: 10.1147/JRD.2017.2713584.

B

Trends and Applications in Stackelberg Security Games. [PDF] By Debarun Kar, Thanh H. Nguyen, Fei Fang, Matthew Brown, Arunesh Sinha, Milind Tambe, Albert Xin Jiang. In HDGT-17: Handbook of Dynamic Game Theory (Edited by Tamar Basar and Georges Zaccour). Springer, 2017.

B

Methods for Addressing the Unpredictable Human Element in Security. [PDF] By (Joint Lead Author) Tracy Cui, Thanh H. Nguyen, James Pita, Richard S. John. In IHSD-17: Improving Homeland Security Decisions, CREATE, 2017.

C

A Stackelberg Game Model for Botnet Traffic Exfiltration. [PDF] By Thanh H. Nguyen, Michael P. Wellman, Satinder Singh. In GameSec-17: Proc. of the 8th Conference on Decision and Game Theory for Security (GameSec), October 2017.

W

Multi-Stage Attack Graph Security Games: Heuristic Strategies, with Empirical Game-Theoretic Analysis. [PDF] By Thanh H. Nguyen, Mason Wright, Michael P. Wellman, Satinder Singh. In MTD-17: ACM Workshop on Moving Target Defense (MTD), October 2017.

2016

B

Towards a Science of Security Games. [PDF] By Thanh H. Nguyen, Debarun Kar, Matthew Brown, Arunesh Sinha, Albert Xin Jiang, Milind Tambe. In STEAM-H-16: New Frontiers of Multidisciplinary Research in STEAM-H, 2016.

C

Combining Graph Contraction and Strategy Generation for Green Security Games. [PDF] By Anjon Basak, Fei Fang, Thanh H. Nguyen, Christopher Kiekintveld. In GameSec-16: Proc. the 7th Conference on Decision and Game Theory for Security (GameSec), November 2016.

C

Three Strategies to Success: Learning Adversary Models in Security Games. [PDF] By Nika Haghtalab, Fei Fang, Thanh H. Nguyen, Arunesh Sinha, Ariel Procaccia, Milind Tambe. In IJCAI-16: Proc. the 25th International Joint Conference on Artificial Intelligence (IJCAI), July 2016.

C

CAPTURE: A New Predictive Anti-Poaching Tool for Wildlife Protection. [PDF] By Thanh H. Nguyen, Arunesh Sinha, Shahrzad Gholami, Andrew Plumptre, Lucas Joppa, Milind Tambe, Margaret Driciru, Fred Wanyama, Aggrey Rwetsiba, Rob Critchlow, Colin Beale. In AAMAS-16: Proc. the 15th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), May 2016. Runner-up of the Best Innovative Application Paper Award at AAMAS-16.

C

Deploying PAWS: Field Optimization of the Protection Assistant for Wildlife Security. [PDF] By Fei Fang, Thanh H. Nguyen, Rob Pickles, Wai Y. Lam, Gopalasamy R. Clements, Bo An, Amandeep Singh, Milind Tambe, Andrew Lemieux. In IAAI-16: Proc. the 28th Innovative Applications of Artificial Intelligence Conference (IAAI), February 2016. Winner of Deployed Application Award at IAAI-16.

S

From the Lab to the Classroom and Beyond: Extending a Game-Based Research Platform for Teaching AI to Diverse Audiences. [PDF] By Nicole Sintov, Debarun Kar, Thanh H. Nguyen, Fei Fang, Kevin Hoffman, Arnaud Lyet, Milind Tambe. In EAAI-16: Proc. the Symposium on Educational Advances in Artificial Intelligence (EAAI), Feb 2016.

W

Addressing Behavioral Uncertainty in Security Games: An Efficient Robust Strategic Solution for Defender Patrols. [PDF] By Thanh H. Nguyen, Arunesh Sinha, Milind Tambe. In ParSocial-16: Proc. IEEE Workshop on Parallel and Distributed Processing for Computational Social Systems, May 2016

2015

J

From Physical Security to Cyber Security. [PDF] By (Joint Lead Author) Arunesh Sinha, Thanh H. Nguyen, Debarun Kar, Matthew Brown, Milind Tambe, Albert Xin Jiang. In JCS-15: the Journal of Cyber Security 2015, 1(1):19-35. DOI: 10.1093/cybsec/tyv007

C

Making the most of Our Regrets: Regret-based Solutions to Handle Payoff Uncertainty and Elicitation in Green Security Games. [PDF] By Thanh H. Nguyen, Francesco M. Delle Fave, Debarun Kar, Aravind S. Lakshminarayanan, Amulya Yadav, Milind Tambe, Noa Agmon, Andrew J. Plumptre, Margaret Driciru, Fred Wanyama, Aggrey Rwetsiba. In GameSec-15: Proc. the 6th Conference on Decision and Game Theory for Security (GameSec), November 2015.

C

Beware the Soothsayer: Evaluating the Reliability of Attack Predictions in Stackelberg and Network Security Games. [PDF] By Benjamin Ford, Thanh H. Nguyen, Nicole Sintov, Milind Tambe, Francesco Delle Fave. In GameSec-15: Proc. the 6th Conference on Decision and Game Theory for Security (GameSec), November 2015.

S

Robust Resource Allocation in Security Games and Ensemble Modeling of Adversary Behavior. [PDF] By Arjun Tambe, Thanh H. Nguyen. In ACMSAC-15: Proc. the ACM Symposium on Applied Computing (ACM SAC) Track, April 2015.

2014

J

Game-Theoretic Target Selection in Contagion-based Domains. [PDF] By Jason Tsai, Thanh H. Nguyen, Nicholas Weller, Milind Tambe. In CJ-14: the Computer Journal 2014, 57(6):893–905. DOI: 10.1093/comjnl/bxt094

C

Regret-based Optimization and Preference Elicitation for Stackelberg Security Games with Uncertainty. [PDF] By Thanh H. Nguyen, Amulya Yadav, Bo An, Milind Tambe, Craig Boutilier. In AAAI-14: Proc. the 28th AAAI Conference on Artificial Intelligence (AAAI), July 2014.

C

Stop the Compartmentalization: Unified Robust Algorithms for Handling Uncertainties in Security Games. [PDF] By Thanh H. Nguyen, Albert Xin Jiang, Milind Tambe. In AAMAS-14: Proc. the 13th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), May 2014.

2013

C

Monotonic Maximin: A Robust Stackelberg Solution Against Boundedly Rational Followers. [PDF] By Albert Xin Jiang, Thanh H. Nguyen, Milind Tambe, Ariel D. Procaccia. In GameSec-13: Proc. the 4th Conference on Decision and Game Theory for Security (GameSec), November 2013.

C

Analyzing the Effectiveness of Adversary Modeling in Security Games. [PDF] By Thanh H. Nguyen, Rong Yang, Amos Azaria, Sarit Kraus, Milind Tambe. In AAAI-13: Proc. the 27th AAAI Conference on Artificial Intelligence (AAAI), July 2013.

C

Modeling Human Adversary Decision Making in Security Games: An Initial Report (Extended Abstract). [PDF] By Thanh H. Nguyen, Amos Azaria, James Pita, Rajiv Maheswaran, Sarit Kraus, Milind Tambe. In AAMAS-13: Proc. the 12th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), May 2013.

2012

C

Security Games for Controlling Contagion. [PDF] By Jason Tsai, Thanh H. Nguyen, Milind Tambe. In AAAI-12: Proc. the 26th AAAI Conference on Artificial Intelligence, July 2012.

S

Security Games on Social Networks. [PDF] By Thanh H. Nguyen, Jason Tsai, Albert Jiang, Emma Bowring, Rajiv Maheswaran, Milind Tambe. In AAAIFallSym-12: Proc. the AAAI Fall Symposium, November 2012.