5 papers
What Does the Server See? Understanding Privacy Leakage from Large Language Models in Split Inference
Mingyuan Fan, Yu Liu, Fuyi Wang +1
The deployment of large language models (LLMs) on resource-constrained devices remains challenging, spurring interest in split inference, where models are partitioned between clien…
PrivGNN: High-Performance Secure Inference for Cryptographic Graph Neural Networks
Fuyi Wang, Zekai Chen, Mingyuan Fan +3
Graph neural networks (GNNs) are powerful tools for analyzing and learning from graph-structured (GS) data, facilitating a wide range of services. Deploying such services in privac…
FLAME: Flexible and Lightweight Biometric Authentication Scheme in Malicious Environments
Fuyi Wang, Fangyuan Sun, Mingyuan Fan +5
Privacy-preserving biometric authentication (PPBA) enables client authentication without revealing sensitive biometric data, addressing privacy and security concerns. Many studies…
Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings
Mingyuan Fan, Fuyi Wang, Cen Chen +1
Federated learning (FL) enables collaborative model training among multiple clients without the need to expose raw data. Its ability to safeguard privacy, at the heart of FL, has r…
Bad-PFL: Exploring Backdoor Attacks against Personalized Federated Learning
Mingyuan Fan, Zhanyi Hu, Fuyi Wang +1
Data heterogeneity and backdoor attacks rank among the most significant challenges facing federated learning (FL). For data heterogeneity, personalized federated learning (PFL) ena…