A visualization system traces jailbreak attacks through LLM layers and neurons, then fine-tunes the vulnerable neurons to reduce attack success while preserving general ability.
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
-
NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models
A visualization system traces jailbreak attacks through LLM layers and neurons, then fine-tunes the vulnerable neurons to reduce attack success while preserving general ability.