Fake authoritative citations matched to the type of harmful request can bypass safety alignment in several commercial and open LLMs.
”Sneakyprompt: Jailbreaking text-to-image gen- erative models.” 2024 IEEE symposium on security and privacy (SP)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Models
Fake authoritative citations matched to the type of harmful request can bypass safety alignment in several commercial and open LLMs.