Skip to content
About
About
About
People
Get Involved with HAI
Support HAI
Research
Research
Research
Fellowship Programs
Grants
Student Affinity Groups
Centers & Labs
Research Publications
Research Partners
Education
Education
Education
Executive and Professional Education
Government and Policymakers
K-12
Stanford Students
Policy
Policy
Policy
Policy Publications
Policymaker Education
Student Opportunities
AI Index
AI Index
AI Index
AI Index Report
Global Vibrancy Tool
People
News
Events
Industry
Centers & Labs
people
Ruoxi Jia
External Bio
Latest Related to Ruoxi Jia
policy brief
Safety Risks from Customizing Foundation Models via Fine-Tuning
Pin-Yu Chen,
Ruoxi Jia,
Tinghao Xie,
Xiangyu Qi,
Yi Zeng,
Prateek Mittal,
Peter Henderson
Natural Language Processing
Foundation Models
Jan 08
This brief underscores the safety risks inherent in custom fine-tuning of large language models.