Skip to content
Research

ENDOPROMPT: Victim-Side Pseudo-References for Utility Degradation.

arXiv:2609.29948v1 Announce Type: new Abstract: Prompt injection can degrade benign task performance without eliciting harmful content. Yet many attack objectives depend on task labels or predefined target responses. We present ENDOPROMPT, a white-box method t

arXiv cs.AIResearch source·