What Hard Tokens Reveal: Exploiting Low-confidence Tokens for Membership Inference Attacks against Large Language Models
Preprint
Jawad, Md Tasnim, Xiao, Mingyan, Wu, Yanzhao. (2026). What Hard Tokens Reveal: Exploiting Low-confidence Tokens for Membership Inference Attacks against Large Language Models
. 10.48550/arxiv.2601.20885
Jawad, Md Tasnim, Xiao, Mingyan, Wu, Yanzhao. (2026). What Hard Tokens Reveal: Exploiting Low-confidence Tokens for Membership Inference Attacks against Large Language Models
. 10.48550/arxiv.2601.20885
