Youzhi Zhang

Home
Publications

Recent Publications (see Google Scholar Profile for the full list)

  • Shuxin Zhuang, Linjian Meng, Shuxin Li, Minming Li, Youzhi Zhang*. Tree-based stochastic optimization for solving large-scale urban network security games. Proceedings of the Fortieth AAAI Conference on Artificial Intelligence(AAAI'26). Accepted.

  • Linjian Meng, Youzhi Zhang*, Zhenxing Ge, Tianpei Yang, Yang Gao. Faster game solving via asymmetry of step sizes. Proceedings of the Fortieth AAAI Conference on Artificial Intelligence(AAAI'26). Accepted.

  • Yi Zhao, Youzhi Zhang. Siren: A learning-based multi-turn attack framework for simulating real-world human jailbreak behaviors. Proceedings of the Annual Computer Security Applications Conference(ACSAC'25). Accepted (Top 11%).

  • Linjian Meng, Youzhi Zhang*, Zhenxing Ge, Tianyu Ding, Shangdong Yang, Zheng Xu, Wenbin Li, Yang Gao. Last-iterate convergence of smooth regret matching+ variants in learning Nash equilibria. Proceedings of the Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS'25). Accepted.

  • Linjian Meng, Tianpei Yang, Youzhi Zhang*, Zhenxing Ge, Shangdong Yang, Tianyu Ding, Wenbin Li, Bo An, Yang Gao. Efficient last-iterate convergence in solving extensive-form games. Proceedings of the Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS'25). Accepted.

  • Linjian Meng, Wubing Chen, Wenbin Li, Tianpei Yang, Youzhi Zhang*, Yang Gao. Reducing variance of stochastic optimization for approximating Nash equilibria in normal-form games. Proceedings of the 42nd International Conference on Machine Learning (ICML'25). Accepted as a Spotlight paper (Top 2.6%).

  • Saurabh Kumar, Valerio La Gatta, Andrea Pugliese, Andrew Pulver, VS Subrahmanian, Jiazhi Zhang, and Youzhi Zhang*. Reinforcement-learning based covert social influence operations. Proceedings of the Web Conference 2025 (WWW'25). Accepted.

  • Wanyuan Wang, Qian Che, Chunyun Liu, Youzhi Zhang, Jiuchuan Jiang, Bo An. Shapley meets DCOP: An unified structural credit assignment for multiagent planning and multiagent reinforcement learning. IEEE Transactions on Automation Science and Engineering. 2025. Accepted.

  • Jingxiang Ma, Hongbin Ma, Youzhi Zhang. TNCOA: Efficient exploration via observation-action constraint on trajectory-based intrinsic reward. CAAI Transactions on Intelligence Technology. 2025. Accepted.

  • Naming Liu, Mingzhi Wang, Xihuai Wang, Weinan Zhang, Yaodong Yang, Youzhi Zhang, Bo An, Ying Wen. Computing ex ante equilibrium in heterogeneous zero-sum team games. Front. Comput. Sci.. 2025. Accepted.

  • Mingi Jeong, Cristian Molinaro, Tonmoay Deb, Youzhi Zhang, Andrea Pugliese, Eugene Santos Jr., V.S. Subrahmanian, Alberto Quattrini Li. Multi-object active search and tracking by multiple agents in untrusted, dynamically changing environments. Autonomous Robots. 2025. Accepted.

  • Zekeng Zeng, Youzhi Zhang, Peipei Yang, Mingyi Zhang, Junge Zhang. Computing approximate Nash equilibrium in two-team zero-sum games by NashConv descent. Proceedings of the 31st International Conference on Neural Information Processing (ICONIP'24). Accepted.

  • Youzhi Zhang, Bo An, Daniel Dajun Zeng. DAG-based column generation for adversarial team games. Proceedings of the 41st International Conference on Machine Learning (ICML'24). Accepted.

  • Runsheng Yu, Youzhi Zhang*, James Kwok. Improving sharpness-aware minimization by lookahead. Proceedings of the 41st International Conference on Machine Learning (ICML'24). Accepted.

  • Changyi Ma, Runsheng Yu, Youzhi Zhang*. A fast similarity matrix calibration method with incomplete query. Proceedings of the Web Conference 2024 (WWW'24). Accepted.

  • Pengdeng Li, Shuxin Li, Xinrun Wang, Jakub Cerny, Youzhi Zhang, Stephen McAleer, Hau Chan, Bo An. Grasper: A generalist pursuer for pursuit-evasion problems. Proceedings of the 23rd International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS'24). Accepted.

  • Tonmoay Deb, Mingi Jeong, Cristian Molinaro, Andrea Pugliese, Alberto Quattrini Li, Eugene Santos Jr., V.S. Subrahmanian, Youzhi Zhang (alphabetical order). Declarative logic-based Pareto-optimal agent decision making. IEEE Transactions on Cybernetics. 2024. Accepted.

  • Natalia Denisenko, Youzhi Zhang, Chiara Pulice, Shohini Bhattasali, Sushil Jajodia, Philip Resnik, V.S. Subrahmanian. A psycholinguistics-inspired method to counter IP theft using fake documents. ACM Transactions on Management Information Systems. 2024. Accepted.

  • Youzhi Zhang, Bo An, V.S. Subrahmanian. Computing optimal Nash equilibria in multiplayer games. Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS'23). Accepted.

  • Shuxin Li, Xinrun Wang, Youzhi Zhang*, Wanqi Xue, Jakub Cerny, Bo An. Solving large-scale pursuit-evasion games using pre-trained strategies. Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI'23). (*Co-Corresponding Author)

  • Tonmoay Deb, Jurgen Dix, Mingi Jeong, Cristian Molinaro, Andrea Pugliese, Alberto Quattrini Li, Eugene Santos, V.S. Subrahmanian, Shanchieh Yang, Youzhi Zhang. DUCK: A drone-urban cyber-defense framework based on Pareto-optimal deontic logic agents. Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI'23) .

  • Youzhi Zhang, Bo An, V.S. Subrahmanian. Finding optimal Nash equilibria in multiplayer games via correlation plans. Proceedings of the 22nd International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS'23), (EA) .

  • Shuxin Li, Youzhi Zhang*, Xinrun Wang, Wanqi Xue, Bo An. Decision making in team-adversary games with combinatorial action space. CAAI Artificial Intelligence Research. 2023.

  • Youzhi Zhang, Sayak Chakrabarty, Rui Liu, Andrea Pugliese, V.S. Subrahmanian. SockDef: A dynamically adaptive defense to a novel attack on review fraud detection engines. IEEE Transactions on Computational Social Systems. 2023. Accepted.

  • Youzhi Zhang, Dongkai Chen, Sushil Jajodia, Andrea Pugliese, V.S. Subrahmanian, Yanhai Xiong. GAIT: A game-theoretic defense against intellectual property theft. IEEE Transactions on Dependable and Secure Computing. 2023. Accepted.

  • Youzhi Zhang, Sayak Chakrabarty, Rui Liu, Andrea Pugliese, V.S. Subrahmanian. A new dynamically changing attack on review fraud systems and a dynamically changing ensemble defense. Proceedings of the 20th IEEE International Conference on Dependable, Autonomic & Secure Computing(DASC'22). Best Paper Award.

  • Youzhi Zhang, Bo An, V.S. Subrahmanian. Correlation-based algorithm for team-maxmin equilibrium in multiplayer extensive-form games. Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI'22). pp.606-612, accepted as Long Oral Presentation (3.75% rate).

  • Wanqi Xue, Youzhi Zhang, Shuxin Li, Bo An, Chai Kiat Yeo. Solving large-scale extensive-form network security games via neural fictitious self-play. Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI'21), pp.3713-3720.

  • Shuxin Li, Youzhi Zhang, Xinrun Wang, Wanqi Xue, Bo An. CFR-MIX: Solving imperfect information extensive-form games with combinatorial action space. Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI'21), pp.3663-3669.

  • Youzhi Zhang, Bo An, Jakub Cerny. Computing ex ante coordinated team-maxmin equilibria in zero-sum multiplayer extensive-form games. Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI'21), pp.5813-5821.

  • Youzhi Zhang, Bo An. Converging to team-maxmin equilibria in zero-sum multiplayer games. Proceedings of the 37th International Conference on Machine Learning (ICML'20), pp.11033-11043.

  • Zhenyu Shi, Runsheng Yu, Xinrun Wang, Rundong Wang, Youzhi Zhang, Hanjiang Lai, Bo An. Learning expensive coordination: An event-based deep RL approach. Proceedings of the 2020 International Conference on Learning Representations (ICLR'20).

  • Youzhi Zhang, Bo An. Computing team-maxmin equilibria in zero-sum multiplayer extensive-form games. Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI'20), pp.2318-2325.

  • Youzhi Zhang, Qingyu Guo, Bo An, Long Tran-Thanh, Nicholas Jennings. Optimal interdiction of urban criminals with the aid of real-time information. Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI'19), pp.1262-1269.

  • Youzhi Zhang, Bo An, Long Tran-Thanh, Nicholas R. Jennings, Zhen Wang, Jiarui Gan. Optimal escape interdiction on transportation networks. Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI'17), pp.3936-3944.