Skip to content
NeurIPS 2026 planner

Poster · Sydney

Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models

When
Tue 8 Dec 2026, 10:00–13:00 AEDT
Where
Hall 1-4, ICC Sydney
Exhibition Centre, Level 1
Session
Sydney Poster Session 1
Authors
Chen Xiong, Zhiyuan HE, Pin-Yu Chen, Ching-Yun Ko, Tsung-Yi Ho
Organisations
The Chinese University of Hong Kong, IBM
QRS classification
Language models, Safety, fairness and privacy

Open in scheduleOfficial page