Xiaojin Zhang

Perturbation-Induced Linearization: Constructing Unlearnable Data with Solely Linear Classifiers

Fed-DIP: Federated Domain Generalization by Synergizing Implicit Disentanglement and Context-Aware Prompting

FedEM: A Privacy-Preserving Framework for Concurrent Utility Preservation in Federated Learning

FedSumUp:Secure Federated Learning Without Client-Side Training for Resource-Constrained Edge Devices

FedEAT: A Robustness Optimization Framework for Federated LLMs

FedCRAP: Federated Critical-Region-Aware Perturbations for Refined Privacy-Preserving Federated Learning

FedBARRE: Privacy–Utility Optimized Perturbation Ensemble against Gradient Leakage Attacks in Federated Learning

Random Projection Against Gradient Leakage: Privacy-Preserving in Federated Learning

TAFS: Task-aware Activation Function Search for Graph Neural Networks