Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections

Yuanpu Cao, Bochuan Cao, Jinghui Chen

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

1 Scopus citations

Fingerprint

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

Keyphrases

Computer Science