EVA applies direct model editing to surgically neutralize jailbreak vulnerabilities in LLMs and VLMs by targeting specific neurons while preserving general capabilities.
Safellm:Unlearningharmfuloutputsfromlargelanguagemodelsagainstjailbreakattacks
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Exclusive Unlearning makes LLMs safe by forgetting all but retained domain knowledge, protecting against jailbreaks while preserving useful responses in areas like medicine and math.
The paper analyzes evolving security and safety threats in generative AI from content generation to agentic actions, noting that attack surfaces expand faster than defenses and that many safeguards require institutional coordination not yet in place.
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.
-
Exclusive Unlearning
Exclusive Unlearning makes LLMs safe by forgetting all but retained domain knowledge, protecting against jailbreaks while preserving useful responses in areas like medicine and math.
-
From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI
The paper analyzes evolving security and safety threats in generative AI from content generation to agentic actions, noting that attack surfaces expand faster than defenses and that many safeguards require institutional coordination not yet in place.