Shabihi, Shayan

2 publications

ICLR 2026 PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic Approach Udari Madhushani Sehwag, Shayan Shabihi, Alex McAvoy, Vikash Sehwag, Yuancheng Xu, Dalton Towers, Furong Huang

ICLRW 2025 AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security Zikui Cai, Shayan Shabihi, Bang An, Zora Che, Brian R. Bartoldson, Bhavya Kailkhura, Tom Goldstein, Furong Huang