影响力指数

-/100

发表论文2 篇

平均评分3.8

年均产出2.0 篇/年

Mohamed Amine Merzouk

Postdoc@Mila - Quebec Artificial Intelligence Institute·加拿大·OpenReview

研究方向

AI Safety and Security · Cybersecurity

Deep-Cover Agents: Long-Horizon Prompt Injections on Production LLM Systems

ICLR 2026Rejected

Latent Personality Alignment: Improving harmlessness without mentioning harms

ICLR 2026Withdrawn

合作者 (6)

David Williams-King