ML Anthology
Authors
Search
About
Renzhe
1 publications
ICLR
2026
A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-Space
Bingjie Zhang
,
Yibo Yang
,
Renzhe
,
Dandan Guo
,
Jindong Gu
,
Philip Torr
,
Bernard Ghanem