作者位次 #4/12ACL 2026Findings· Findings of ACL
Towards Provably Secure Generative AI : Reliable Consensus Sampling
Yu Cui · Hang Fu · Sicheng Pan · Zhuoyu Sun · Yifei Liu · Yuhong Nie · Bo Ran · Baohan Huang · Xufeng Zhang · Haibin Zhang · Cong Zuo · Licheng Wang
摘要
Existing research on generative AI security is primarily driven by mutually reinforcing attack and defense methodologies grounded in empirical experience. This dynamic frequently gives rise to previously unknown attacks that can circumvent current detection and prevention. This necessitates the c...