Adversarial attacks and defenses on Graph Neural Networks.

CanarySEFI is a framework for evaluating the robustness of deep learning-based image recognition models. It can evaluate model robustness and attack/defense algorithm effectiveness, encompassing 26…

Implementation of paper "More is Better (Mostly): On the Backdoor Attacks in Federated Graph Neural Networks"

Federated learning on graph, especially on graph neural networks (GNNs), knowledge graph, and private GNN.

THU-AIR Vertical Federated Learning general, extensible and light-weight framework

The code of the attack scheme in the paper "Backdoor Attack Against Split Neural Network-Based Vertical Federated Learning"

This is the source code for MEA-Defender. Our paper is accepted by the IEEE Symposium on Security and Privacy (S&P) 2024.

A self-developed customized file manager(file explorer).