Zhengyi Li
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1AI×1
Frequent co-authors
Research Timeline
2026
On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference
This paper demonstrates a novel attack against the shuffling defense used in secure Transformer inference, showing that randomly permuted activations can still be exploited to recover model weights.
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.AIRecentMay 6, 2026
On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference
Zhengyi Li, Yakai Wang, Kang Yang, Yu Yu +5 more
This paper demonstrates a novel attack against the shuffling defense used in secure Transformer inference, showing that randomly permuted activations can still be exploited to recover model weights.
View →