Chaozhuo Li
2 papers · Latest:
Cryptography & Security
Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution
EvoSafety introduces a novel framework for lifelong, model-agnostic LLM safety via externalized attack-defense co-evolution to counter adversarial prompts.
2605.13411
Cryptography & SecurityTwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning
TwinGate uses asymmetric contrastive learning to defend LLMs against decompositional jailbreaks in untraceable traffic with high efficiency.
2604.27861
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.