Jingqiao Xiu
Papers
4
Total Citations
20
H-Index
3
About
Jingqiao Xiu is an emerging researcher specializing in the security and robustness of multi-agent reinforcement learning (MARL) systems, with a particular focus on adversarial vulnerabilities in cooperative settings. His work addresses a critical gap in artificial intelligence safety: understanding and defending against attacks on cooperative multi-agent systems before their real-world deployment. Xiu's most recognized contribution, "Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence," has accumulated citations across multiple versions since 2023, demonstrating sustained community interest in his findings. This work probes how a minority of adversarial agents can undermine the collective behavior of cooperative systems, challenging assumptions about white-box attack constraints and exposing previously overlooked vulnerabilities. Complementing this, his research on mutual information regularization offers a promising defense framework, addressing the exponential complexity of multi-agent perturbation scenarios to enhance robustness under worst-case conditions. With a growing citation record and publications spanning 2023 to 2025, Xiu represents a rising voice in the intersection of MARL, adversarial machine learning, and AI safety — areas of increasing importance as autonomous multi-agent systems move closer to real-world applications.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4