Most large language model services use stateless defenses, which judge only the current request, to refuse harmful tasks. Decomposition attacks exploit this limitation by splitting a harmful task into individually permissible requests and combining their answers. Defending against them therefore requires a stateful mon...
Bowen Sun, Zhengyue Zhao, Xiaogeng Liu et al.· 1 citation
Large language models remain vulnerable to jailbreaks, and automated red teaming is the standard way to find jailbreaks in large language models at scale. Current methods either draw more samples at test time through search, rewriting, and tree expansion, or train a stronger attacker offline with reinforcement learning...
Tong-Yan Hu, Hao Li, Xiaogeng Liu et al.· 0 citations
EvoSafeHarness is a safety-specific optimization framework that synthesizes a deployable harness for a frozen model in a target domain, guided by model behavior, domain specifications, and fresh-context adversarial review to reject benchmark-specific rules.
Nanxi Li, Ying-Zi Ma, Yulong Cao et al.· 2 citations
KeyPooling is presented, a measurement method that traces customer identity through cache lookup and write, verifies runtime transformations, and tests one predicted identity component at a time, and derives a defense contract.
Bowen Sun, Yixi Cai, Xiaogeng Liu et al.· 0 citations
