نسخة أولية وصول مفتوح
OPBackdoor: Opportunistic Backdoors via Alibi-Aligned Reasoning
When a backdoor trigger activates the target response regardless of the triggered prompt context, the backdoor objective reveals itself. Challenging this trigger-sufficient formulation across the LLM backdoor literature, we introduce Opportunistic Backdoors (OPBackdoor), in which the backdoor objective is elicited only …