3 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
ENDOPROMPT is a white-box method that learns utility-degrading prefixes from unlabeled instructions that yields a mean utility change of -26.8 percentage points across four instruction-tuned models and the complete splits of seven benign benchmarks.
PsychJail is presented, a psychology-guided framework for red teaming aligned LLMs through theory-grounded, multi-turn persuasion and establishes psychological jailbreaks as a distinct red-teaming frontier for increasingly interactive LLMs.
This work proposes Wrapper-Based Intent-Form Augmentation (WIFA), an automatic intent-group augmentation method that pairs wrapped harmful examples with structurally matched wrapped benign counterexamples, requiring no external teacher or manual per-wrapper intent labels.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
