AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

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

NeurIPS 2021 · Adversarial robustness and security › Attacks on text and graphs · approach: Graph neural network robustness · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add layer normalization to GML modelsVarious GML models · Five GRB datasets, adversarial robustness evaluationaccuracyImproved
Train with adversarial examples generated by graph modification or injectionVarious GML models · Five GRB datasets, adversarial robustness evaluationaccuracyImproved
Attack lower-degree target nodes rather than higher-degree target nodesGraph injection attacks · GRB datasets, Easy/Medium/Hard test subsetsaccuracyHurt
Use GAT or GIN instead of other vanilla GML model architecturesVanilla GML models · Several GRB datasets, graph injection scenarioaccuracy under attackImproved
Use high-order message propagation architectures such as APPNP or SGCNVanilla GML models · GRB datasets, graph injection scenarioaccuracy under attackHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy