A single weight matrix edit, guided by a multi-node target vector, injects a universal jailbreak backdoor into safety-aligned LLMs in minutes.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Injecting Universal Jailbreak Backdoors into LLMs in Minutes
A single weight matrix edit, guided by a multi-node target vector, injects a universal jailbreak backdoor into safety-aligned LLMs in minutes.