1 citations · 1 across the 4 of their papers we have counts for
4 papers
CrypFormBench: Benchmarking Formal Analysis Capability of Large Language Models for Cryptographic Schemes
Zhaoxuan Li, Qionglu Zhang, Hengyuan Liu +8
Manual formal analysis of cryptographic schemes is labor-intensive and requires substantial expertise. While model-checking tools (e.g., Scyther and Tamarin) and computational-secu…
Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks
Haotian Jin, Yang Li, Haihui Fan +3
Backdoor attacks pose a serious threat to the security of large language models (LLMs), causing them to exhibit anomalous behavior under specific trigger conditions. The design of…
Towards Confidential and Efficient LLM Inference with Dual Privacy Protection
Honglan Yu, Yibin Wang, Feifei Dai +3
CPU-based trusted execution environments (TEEs) and differential privacy (DP) have gained wide applications for private inference. Due to high inference latency in TEEs, researcher…
An Extension of the Beurling-Chen-Hadwin-Shen Theorem for Noncommutative Hardy Spaces Associated with Finite von Neumann Algebras
Haihui Fan, Don Hadwin, Wenjing Liu
In 2015, Yanni Chen, Don Hadwin and Junhao Shen proved a noncommutative version of Beurling's theorems for a continuous unitarily invariant norm on a tracial von Neumann alge…