Skip to main navigation Skip to search Skip to main content

Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Fingerprint

Dive into the research topics of 'Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections'. Together they form a unique fingerprint.
Sort by

Keyphrases

Computer Science