Released RL prompt injection attacker checkpoints from PIForge and PISmith.
Albert Yin
AlbertYin
AI & ML interests
LLM
Recent Activity
upvoted a paper about 15 hours ago
GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis upvoted a paper 1 day ago
PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses updated a collection 6 days ago
PIForge AttackersOrganizations
None yet