EVA applies direct model editing to surgically neutralize jailbreak vulnerabilities in LLMs and VLMs by targeting specific neurons while preserving general capabilities.
Jailbreaking black box large language models in twenty queries,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
EVA: Editing for Versatile Alignment against Jailbreaks
EVA applies direct model editing to surgically neutralize jailbreak vulnerabilities in LLMs and VLMs by targeting specific neurons while preserving general capabilities.