AGNNCert: Defending Graph Neural Networks against Arbitrary Perturbations with Deterministic Certification

• URL: http://arxiv.org/abs/2502.00765v1
• Date: Sun, 02 Feb 2025 11:56:42 GMT
• Title: AGNNCert: Defending Graph Neural Networks against Arbitrary Perturbations with Deterministic Certification
• Authors: Jiate Li, Binghui Wang,
• Abstract summary: Graph neural networks (GNNs) are vulnerable to adversarial perturbations. AGNNCert is the first certified defense for GNNs against arbitrary (edge, node, and node feature) perturbations.
• Score: 14.288781140044465
• License:
• Abstract: Graph neural networks (GNNs) achieve the state-of-the-art on graph-relevant tasks such as node and graph classification. However, recent works show GNNs are vulnerable to adversarial perturbations include the perturbation on edges, nodes, and node features, the three components forming a graph. Empirical defenses against such attacks are soon broken by adaptive ones. While certified defenses offer robustness guarantees, they face several limitations: 1) almost all restrict the adversary's capability to only one type of perturbation, which is impractical; 2) all are designed for a particular GNN task, which limits their applicability; and 3) the robustness guarantees of all methods except one are not 100% accurate. We address all these limitations by developing AGNNCert, the first certified defense for GNNs against arbitrary (edge, node, and node feature) perturbations with deterministic robustness guarantees, and applicable to the two most common node and graph classification tasks. AGNNCert also encompass existing certified defenses as special cases. Extensive evaluations on multiple benchmark node/graph classification datasets and two real-world graph datasets, and multiple GNNs validate the effectiveness of AGNNCert to provably defend against arbitrary perturbations. AGNNCert also shows its superiority over the state-of-the-art certified defenses against the individual edge perturbation and node perturbation.

Related papers

• GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models [32.513071094162726]
  Graph neural networks (GNNs) have exhibited superior performance in various classification tasks on graph-structured data. Link stealing attacks pose severe security and privacy threats to the training graph used in GNN models. We propose a novel solution, called Graph Link Disguise (GRID), to defend against link stealing attacks.
  arXiv  Detail & Related papers  (2025-01-19T08:39:22Z)
• Exact Certification of (Graph) Neural Networks Against Label Poisoning [50.87615167799367]
  Machine learning models are vulnerable to label flipping, i.e., the adversarial modification (poisoning) of training labels to compromise performance. We introduce an exact certification method, deriving both sample-wise and collective certificates. Our work presents the first exact certificate to a poisoning attack ever derived for neural networks, which could be of independent interest.
  arXiv  Detail & Related papers  (2024-11-30T17:05:12Z)
• HGAttack: Transferable Heterogeneous Graph Adversarial Attack [63.35560741500611]
  Heterogeneous Graph Neural Networks (HGNNs) are increasingly recognized for their performance in areas like the web and e-commerce. This paper introduces HGAttack, the first dedicated gray box evasion attack method for heterogeneous graphs.
  arXiv  Detail & Related papers  (2024-01-18T12:47:13Z)
• Graph Agent Network: Empowering Nodes with Inference Capabilities for Adversarial Resilience [50.460555688927826]
  We propose the Graph Agent Network (GAgN) to address the vulnerabilities of graph neural networks (GNNs) GAgN is a graph-structured agent network in which each node is designed as an 1-hop-view agent. Agents' limited view prevents malicious messages from propagating globally in GAgN, thereby resisting global-optimization-based secondary attacks.
  arXiv  Detail & Related papers  (2023-06-12T07:27:31Z)
• Resisting Graph Adversarial Attack via Cooperative Homophilous Augmentation [60.50994154879244]
  Recent studies show that Graph Neural Networks are vulnerable and easily fooled by small perturbations. In this work, we focus on the emerging but critical attack, namely, Graph Injection Attack. We propose a general defense framework CHAGNN against GIA through cooperative homophilous augmentation of graph data and model.
  arXiv  Detail & Related papers  (2022-11-15T11:44:31Z)
• Uncertainty-Matching Graph Neural Networks to Defend Against Poisoning Attacks [43.60973654460398]
  Graph Neural Networks (GNNs) are generalizations of neural networks to graph-structured data. GNNs are vulnerable to adversarial attacks, i.e., a small perturbation to the structure can lead to a non-trivial performance degradation. We propose Uncertainty Matching GNN (UM-GNN), that is aimed at improving the robustness of GNN models.
  arXiv  Detail & Related papers  (2020-09-30T05:29:42Z)
• Graph Backdoor [53.70971502299977]
  We present GTA, the first backdoor attack on graph neural networks (GNNs) GTA departs in significant ways: it defines triggers as specific subgraphs, including both topological structures and descriptive features. It can be instantiated for both transductive (e.g., node classification) and inductive (e.g., graph classification) tasks.
  arXiv  Detail & Related papers  (2020-06-21T19:45:30Z)
• GNNGuard: Defending Graph Neural Networks against Adversarial Attacks [16.941548115261433]
  We develop GNNGuard, an algorithm to defend against a variety of training-time attacks that perturb the discrete graph structure. GNNGuard learns how to best assign higher weights to edges connecting similar nodes while pruning edges between unrelated nodes. Experiments show that GNNGuard outperforms existing defense approaches by 15.3% on average.
  arXiv  Detail & Related papers  (2020-06-15T06:07:46Z)
• AN-GCN: An Anonymous Graph Convolutional Network Defense Against Edge-Perturbing Attack [53.06334363586119]
  Recent studies have revealed the vulnerability of graph convolutional networks (GCNs) to edge-perturbing attacks. We first generalize the formulation of edge-perturbing attacks and strictly prove the vulnerability of GCNs to such attacks in node classification tasks. Following this, an anonymous graph convolutional network, named AN-GCN, is proposed to counter edge-perturbing attacks.
  arXiv  Detail & Related papers  (2020-05-06T08:15:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.