NLPExplorer
Papers
Venues
Authors
Authors Timeline
Field of Study
URLs
ACL N-gram Stats
TweeNLP
API
Team
Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections
Yuanpu Cao
|
Bochuan Cao
|
Jinghui Chen
|
Paper Details:
Month: June
Year: 2024
Location: Mexico City, Mexico
Venue:
NAACL |
Citations
URL
No Citations Yet
https://trojandetection.ai/
https://openai.com/blog/
https://github.com/CaoYuanpu/BackdoorUnalign
Field Of Study