EvoSafety achieves model-agnostic lifelong LLM safety via external adversarial skill libraries for red-teaming and a lightweight memory-augmented defense model that operates in steer or guard modes, reaching 99.61% defense success.
- **Numeric equivalence**: same numeric value up to normal rounding (e.g., ‘1/2‘ == ‘0.5‘; ‘sqrt(2)/2‘ == ‘1/sqrt(2)‘)
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
-
Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution
EvoSafety achieves model-agnostic lifelong LLM safety via external adversarial skill libraries for red-teaming and a lightweight memory-augmented defense model that operates in steer or guard modes, reaching 99.61% defense success.