4 papers
Decision-Level Hijacking: Injecting Cognitive Bias into Large Language Models via Bit-Flip Attacks
Yu Yan, Jiahao Chen, Siqi Lu +6
Large Language Models (LLMs) have been widely applied in high-stakes decision-making scenarios such as corporate strategy, and users are increasingly relying on their outputs. Howe…
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…
Has the Two-Decade-Old Prophecy Come True? Artificial Bad Intelligence Triggered by Merely a Single-Bit Flip in Large Language Models
Yu Yan, Siqi Lu, Yang Gao +4
Recently, Bit-Flip Attack (BFA) has garnered widespread attention for its ability to compromise software system integrity remotely through hardware fault injection. With the widesp…
Magnifier: Detecting Network Access via Lightweight Traffic-based Fingerprints
Wenhao Li, Qiang Wang, Huaifeng Bao +3
Network access detection plays a crucial role in global network management, enabling efficient network monitoring and topology measurement by identifying unauthorized network acces…