EvoDefense: Co-Evolving Black-Box Defense with Large Language Models
Researchers have developed EvoDefense, a novel approach to protect large language models (LLMs) from attacks in black-box scenarios. This system uses a guard LLM and an experience memory to continuously refine defense strategies through an iterative attack-defense evolution loop. EvoDefense demonstrates strong generalization capabilities, effectively defending against unseen attacks and various LLM architectures without requiring retraining. AI
IMPACT Enhances LLM security by providing a dynamic defense mechanism against evolving adversarial attacks.