arXiv:2605. 26595v1 Announce Type: new Abstract: Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison.
Paper
Cordyceps: Covert Control Attacks on LLMs via Data Poisoning
Unreadunread
Paper
Unreadunread
arXiv:2605. 26595v1 Announce Type: new Abstract: Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison.