Showing cs.CRShow all
2 papers · 1 filter
cs.CR2025
ShieldMMU: Detecting and Defending against Controlled-Channel Attacks in Shielding Memory System
Gang Liu, Ningjie Li, Cen Chen
Intel SGX and hypervisors isolate non-privileged programs from other software, ensuring confidentiality and integrity. However, side-channel attacks continue to threaten Intel SGX'…
cs.CR2025
FLTG: Byzantine-Robust Federated Learning via Angle-Based Defense and Non-IID-Aware Weighting
Yanhua Wen, Lu Ai, Gang Liu +2
Byzantine attacks during model aggregation in Federated Learning (FL) threaten training integrity by manipulating malicious clients' updates. Existing methods struggle with limited…