Graph Robustness Benchmark: Benchmarking the Adversarial Robustness of Graph Machine Learning

Qinkai Zheng, Xu Zou, Yuxiao Dong, Yukuo Cen, Da Yin, Jiarong Xu, Yang Yang, Jie Tang

Keywords: adversarial robustness, graph machine learning, benchmark

TL;DR: Benchmark for better evaluating the adversarial robustness of graph machine learning models

Abstract:

Adversarial attacks on graphs have posed a major threat to the robustness of graph machine learning (GML) models. Naturally, there is an ever-escalating arms race between attackers and defenders. However, the strategies behind both sides are often not fairly compared under the same and realistic conditions. To bridge this gap, we present the Graph Robustness Benchmark (GRB) with the goal of providing a scalable, unified, modular, and reproducible evaluation for the adversarial robustness of GML models. GRB standardizes the process of attacks and defenses by 1) developing scalable and diverse datasets, 2) modularizing the attack and defense implementations, and 3) unifying the evaluation protocol in refined scenarios. By leveraging the modular GRB pipeline, the end-users can focus on the development of robust GML models with automated data processing and experimental evaluations. To support open and reproducible research on graph adversarial learning, GRB also hosts public leaderboards for different scenarios.
As a starting point, we provide various baseline experiments to benchmark the state-of-the-art techniques. GRB is an open-source benchmark and all datasets, code, and leaderboards are available at https://cogdl.ai/grb/home.

URL: Homepage: https://cogdl.ai/grb/home ; Code: https://github.com/THUDM/grb

Contribution Process Agreement: Yes

Dataset Url: https://cogdl.ai/grb/home

License: MIT License

Author Statement: Yes