SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation
Paper • 2608.21500 • Published • 41
Sizhe Chen PRO
Sizhe-Chen
AI & ML interests
trustworthy machine learning, AI security
Recent Activity
published a model 4 days ago
Sizhe-Chen/Qwen3.8-27B-Thinking-SecOPD updated a model 9 days ago
Sizhe-Chen/Qwen3.8-27B-Thinking-SecOPD updated a model 9 days ago
Sizhe-Chen/Qwen3.6-27B-Instruct-MetaSecAlignOrganizations
upvoted a paper 2 months ago