Institute of Information Engineering

LLMDPA: pre-execution privacy auditing of DP-SGD via evidence-constrained semantic analysis

Abstract Privacy auditing has emerged as a critical component for safeguarding data privacy in machine learning models. Existing empirical auditing methods heavily rely on model runtime states or post-deployment interfaces, resulting in substantial time costs and limited source-l...

Terminal-Assisted Web Authentication for Shared Devices with BLE-Based Confirmation Gating

In shared-device scenarios, terminal-assisted Web authentication reduces credential exposure by keeping authentication credentials on a user-carried mobile terminal. However, existing methods struggle to minimize mobile interaction while protecting against account misuse by other...

CSCProv: causal-semantic consistent provenance graph compression for attack detection

Abstract Provenance graphs have become an important foundation for attack investigation and anomaly detection in enterprise systems. However, system audit logs generate massive numbers of events, resulting in extremely large provenance graphs that not only hinder efficient securi...

CritiFlip: an efficient bit-flip attack based on critical weight identification

Abstract Recent studies have demonstrated that deep neural networks (DNNs) are highly vulnerable to bit-flip attacks (BFAs), where modifying only a few bits in memory can severely degrade model performance. However, existing BFA techniques typically rely on exhaustive searches ov...