Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
AbstractHidden tokens plus a stage controller make the backdoor progressively corrupt reasoning upon triggering, and the authors believe that looking only at the answer will miss it.
Cancerous Backdoor Attack changes LLM backdoors from one-time activation to multi-stage reasoning corruption that accumulates progressively with triggers.
AbstractThe authors state that jailbreaks arise from competition between two types of heads, and that HCS plus distillation can use this competition for inference-time intervention.
The authors use attention head mechanism analysis for continuation-triggered jailbreaks: under the same harmful instruction, moving the continuation suffix from after the instruction to outside the prompt boundary makes the model more likely to continue generating along the suffix.