Cancerous Backdoor Attack: Gradual Activation via Invisible Tokens and A Stage Controller

본문 미리보기

arXiv:2610.12644v1 Announce Type: new Abstract: Backdoor Attacks on Large Language Models (LLMs) typically follow a trigger-response pattern, where satisfying a trigger condition activates a single terminal behavior. However, this single-point backdoor activation does not explore attacks in which malicious behavior develops gradually through multiple intermediate stages before reaching the terminal activation stage. We present Cancerous Backdoor Attack, that gradually corrupts an LLM's reasonin