Skip to content
NeurIPS 2026 planner

Poster · Sydney

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models

When
Wed 9 Dec 2026, 17:00–20:00 AEDT
Where
Hall 1-4, ICC Sydney
Exhibition Centre, Level 1
Session
Sydney Poster Session 4
Authors
Hayden Helm, Xiaodong Liu, Weiwei Yang
Organisations
Helivan, Microsoft, Asemic.ai
QRS classification
Safety, fairness and privacy

Open in scheduleOfficial page