본문으로 건너뛰기

#Indirect Prompt Injection

3개의 포스트

[논문리뷰] One Polluted Page Is Enough: Evaluating Web Content Pollution in LLM Recommenders

댓글 수 로딩 중

[논문리뷰] ToolHazard: Scaling Adversarial Environments for Security Evaluation and Alignment of LLM-based Agents

댓글 수 로딩 중