I'm a PhD Candidate specializing in the Security of AI in Multi-Agent Reinforcement Learning (MARL). My work focuses on understanding vulnerabilities in heterogeneous agent systems to build more robust and secure AI.
- ๐ก๏ธ I research adversarial attacks and defense mechanisms in multi-agent environments.
- ๐ฒ๐ฆ I co-founded the Moroccan Mathematical Community.
- ๐ I document my research and thoughts at hambam.top.


