Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks
Paper • 2605.19147 • Published
John Halloran
johnhalloran
AI & ML interests
None yet
Recent Activity
submitted a paper about 9 hours ago
Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks liked a model 9 months ago
huihui-ai/Huihui-gpt-oss-20b-BF16-abliterated authored a paper about 1 year ago
MCP Safety Audit: LLMs with the Model Context Protocol Allow Major
Security ExploitsOrganizations
None yet
submitted a
paper to Daily Papers about 9 hours ago
authored a
paper about 1 year ago
authored a
paper over 1 year ago