Single-Node Attacks for Fooling Graph Neural Networks
arXiv:2011.03574 · doi:10.1016/j.neucom.2022.09.115
Abstract
Graph neural networks (GNNs) have shown broad applicability in a variety of domains. These domains, e.g., social networks and product recommendations, are fertile ground for malicious users and behavior. In this paper, we show that GNNs are vulnerable to the extremely limited (and thus quite realistic) scenarios of a single-node adversarial attack, where the perturbed node cannot be chosen by the attacker. That is, an attacker can force the GNN to classify any target node to a chosen label, by only slightly perturbing the features or the neighbor list of another single arbitrary node in the graph, even when not being able to select that specific attacker node. When the adversary is allowed to select the attacker node, these attacks are even more effective. We demonstrate empirically that our attack is effective across various common GNN types (e.g., GCN, GraphSAGE, GAT, GIN) and robustly optimized GNNs (e.g., Robust GCN, SM GCN, GAL, LAT-GCN), outperforming previous attacks across different real-world datasets both in a targeted and non-targeted attacks. Our code is available at https://github.com/benfinkelshtein/SINGLE .
arXiv commentAppeared in Neurocomputing
References in corpus (14)
- Explaining and Harnessing Adversarial Examples
- Intriguing properties of neural networks
- Inductive Representation Learning on Large Graphs
- Simplifying Graph Convolutional Networks
- Adversarial Attacks on Neural Networks for Graph Data
- Pitfalls of Graph Neural Network Evaluation
- Adversarial Attacks on Graph Neural Networks via Meta Learning
- Hiding Individuals and Communities in a Social Network
- Fast Gradient Attack on Network Embedding
- GNNGuard: Defending Graph Neural Networks against Adversarial Attacks
- Certifiable Robustness and Robust Training for Graph Convolutional Networks
- "Like Sheep Among Wolves": Characterizing Hateful Users on Twitter
- Reliable Graph Neural Networks via Robust Aggregation
- Information Obfuscation of Graph Neural Networks