paper-with-me

홈 › Papers

Are Defenses for Graph Neural Networks Robust?

2023-01-31 · Felix Mujkanovic, Simon Geisler, Stephan Günnemann, Aleksandar Bojchevski

A cursory reading of the literature suggests that we have made a lot of progress in designing effective adversarial defenses for Graph Neural Networks (GNNs). Yet, the standard methodology has a serious flaw - virtually all of the defenses are evaluated against non-adaptive attacks leading to overly optimistic robustness estimates. We perform a thorough robustness analysis of 7 of the most popular defenses spanning the entire spectrum of strategies, i.e., aimed at improving the graph, the architecture, or the training. The results are sobering - most defenses show no or only marginal improvement compared to an undefended baseline. We advocate using custom adaptive attacks as a gold standard and we outline the lessons we learned from successfully designing such attacks. Moreover, our diverse collection of perturbed graphs forms a (black-box) unit test offering a first glance at a model's robustness.

📄 PDF Abstract BibTeX arXiv:2301.13694

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studies

2020-03-02 · Wei Jin, Ya-Xin Li, Han Xu, Yiqi Wang 외

Deep neural networks (DNNs) have achieved significant performance in various tasks. However, recent studies have shown that DNNs can be easily fooled by small perturbation on the input, called adversarial attacks. As the…

Adversarial Attack

GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?

2026-05-12 · Kaixiang Zhao, Bolin Shen, Yuyang Dai, Shayok Chakraborty 외 arxiv

Graph neural networks (GNNs) deployed as cloud services can be stolen through model-extraction attacks, which train a surrogate from query responses to reproduce the target's behavior, and a growing line of ownership def…

Graph Neural Network

Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbations

2025-03-24 · CVPR 2025 1 · Jiate Li, Meng Pang, Yun Dong, Binghui Wang

Graph neural networks (GNNs) are becoming the de facto method to learn on the graph data and have achieved the state-of-the-art on node and graph classification tasks. However, recent works show GNNs are vulnerable to tr…

Graph Classification

Enhancing O-RAN Security: Evasion Attacks and Robust Defenses for Graph Reinforcement Learning-based Connection Management

2024-05-06 · Ravikumar Balakrishnan, Marius Arvinte, Nageen Himayat, Hosein Nikopour 외

Adversarial machine learning, focused on studying various attacks and defenses on machine learning (ML) models, is rapidly gaining importance as ML is increasingly being adopted for optimizing wireless systems such as Op…

Deep Reinforcement LearningGraph Neural NetworkManagement

A Hard Label Black-box Adversarial Attack Against Graph Neural Networks

2021-08-21 · Jiaming Mu, Binghui Wang, Qi Li, Kun Sun 외

Graph Neural Networks (GNNs) have achieved state-of-the-art performance in various graph structure related tasks such as node classification and graph classification. However, GNNs are vulnerable to adversarial attacks. …

Adversarial AttackClassificationGraph ClassificationGraph Generation+1