EvoDefense: Co-Evolving Black-Box Defense with Large Language Models

EvoDefense: Co-Evolving Black-Box Defense with Large Language Models arXiv:2605.31140v1 Announce Type: new Abstract: Large Language Models (LLMs) remain highly vulnerable to diverse attacks, particularly in black-box settings where the internals of target models are inaccessible. Existing black-box defenses typically rely on pre-defined filtering heuristics, which often fail to generalize to unseen attack types and target model architectures. We introduce EvoDefense, an expe…

https://arxiv.org/abs/2605.31140

sha256:b7dc25a50489cd61a98de6b55690e5389c9f1e0d072e0d5f392f990d64170746

• cve0
• md50
• url0
• ipv40
• ipv60
• sha10
• domain0
• sha2560
• malware_token0
• attack_pattern0
• threat_actor_token0