About
People
Publications
Open Source
Demos
Events
Blog
Careers
Contact
English
English
Français
ServiceNow
ServiceNow AI Research
People
Chris Cundy
ServiceNow AI Research
Chris Cundy
Publications
No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms
.
Joshua Kazdan
,
Abhay Puri
,
Rylan Schaeffer
,
Lisa Yu
,
Chris Cundy
,
Jason Stanley
,
Sanmi Koyejo
,
Krishnamurthy (Dj) Dvijotham
. At
International Conference on Learning Representations, 2026.
PDF
Cite
Cite
×