Skip to content
Sagan

Paper

Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks

Unreadunread

AI summary

arXiv:2605. 19147v1 Announce Type: new Abstract: Large language models (LLMs) are highly susceptible to backdoor attacks (BAs), wherein training samples are poisoned using trigger-based harmful content.