Jiakai Wang
Papers
2
Total Citations
14
H-Index
2
About
Jiakai Wang is a rising researcher whose work sits at the critical intersection of artificial intelligence, multi-agent systems, and adversarial machine learning. His primary focus is on understanding and exposing vulnerabilities in cooperative multi-agent reinforcement learning (MARL) environments—a domain essential for applications ranging from autonomous drone swarms to collaborative robotics. Wang’s most significant contribution is his pioneering study on adversarial minority influence, where he demonstrates how a single malicious agent can systematically corrupt the collective behavior of an entire cooperative team. This work, published in 2024 and 2025, has already garnered 7 citations each, signaling its immediate relevance and impact in the security community. By revealing these subtle yet devastating attack vectors, Wang not only advances the theoretical understanding of robustness in MARL but also provides a crucial foundation for designing more resilient multi-agent systems. His research serves as a wake-up call for the field, emphasizing that as AI systems become more collaborative, they also become more susceptible to targeted manipulation. For students and researchers, Wang’s work is an essential guide to the emerging frontier of adversarial dynamics in cooperative AI.
Research Focus
Key Achievements
Top Papers
- 1
- 2