Graph Adversarial Immunization for Certifiable Robustness
Not on the map. Why?
Abstract (arXiv)
Despite achieving great success, graph neural networks (GNNs) are vulnerable to adversarial attacks. Existing defenses focus on developing adversarial training or model modification. In this paper, we propose and formulate graph adversarial immunization, i.e., vaccinating part of graph structure to improve certifiable robustness of graph against any admissible adversarial attack. We first propose edge-level immunization to vaccinate node pairs. Unfortunately, such edge-level immunization cannot defend against emerging node injection attacks, since it only immunizes existing node pairs. To this end, we further propose node-level immunization. To avoid computationally intensive combinatorial optimization associated with adversarial immunization, we develop AdvImmune-Edge and AdvImmune-Node algorithms to effectively obtain the immune node pairs or nodes. Extensive experiments demonstrate the superiority of AdvImmune methods. In particular, AdvImmune-Node remarkably improves the ratio of robust nodes by 79%, 294%, and 100%, after immunizing only 5% of nodes. Furthermore, AdvImmune methods show excellent defensive performance against various attacks, outperforming state-of-the-art defenses. To the best of our knowledge, this is the first attempt to improve certifiable robustness from graph data perspective without losing performance on clean graphs, providing new insights into graph adversarial learning.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 49 of its 67 references that are in the map. First posted on arXiv 16 Feb 2023.
Builds on
49 of 67 references.
References · 49
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2017Graph Attention Networkscited by 8,854
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2017Inductive Representation Learning on Large Graphscited by 6,284
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
- 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
- 2019Graph Neural Networks for Social Recommendationcited by 711
- 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 663
- 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
- 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
- 2018Adversarial Attack on Graph Structured Datacited by 300
37 more
- 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
- 2021A Comprehensive Survey on Graph Anomaly Detection with Deep Learningcited by 230
- 2017struc2vec: Learning Node Representations from Structural Identitycited by 214
- 2019Topology Attack and Defense for Graph Neural Networks: An Optimization Perspectivecited by 196
- 2020GNNGuard: Defending Graph Neural Networks against Adversarial Attackscited by 195
- 2018Adaptive Sampling Towards Fast Graph Representation Learningcited by 180
- 2018Adversarial Attack and Defense on Graph Data: A Surveycited by 166
- 2019Graph Wavelet Neural Networkcited by 131
- 2018DeepInf: Social Influence Prediction with Deep Learningcited by 128
- 2018Adversarial Attacks on Node Embeddings via Graph Poisoningcited by 109
- 2019Graph Adversarial Training: Dynamically Regularizing Based on Graph Structurecited by 93
- 2018Bayesian graph convolutional neural networks for semi-supervised classificationcited by 88
- 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 88
- 2019A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding Modelscited by 68
- 2021TDGIA:Effective Injection Attacks on Graph Neural Networkscited by 67
- 2019Certifiable Robustness to Graph Perturbationscited by 62
- 2019Certifiable Robustness and Robust Training for Graph Convolutional Networkscited by 59
- 2019Transferring Robustness for Graph Neural Network Against Poisoning Attackscited by 58
- 2020Robust Optimization as Data Augmentation for Large-scale Graphscited by 58
- 2020Certified Robustness of Graph Neural Networks against Adversarial Structural Perturbationcited by 57
- 2020Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and Morecited by 56
- 2019Attacking Graph-based Classification via Manipulating the Graph Structurecited by 53
- 2020Scalable Attack on Graph Data by Injecting Vicious Nodescited by 50
- 2020Graph Convolutional Networks using Heat Kernel for Semi-supervised Learningcited by 50
- 2021Single Node Injection Attack against Graph Neural Networkscited by 45
- 2020Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studiescited by 42
- 2020A Survey of Adversarial Learning on Graphscited by 42
- 2020Adversarial Attack on Large Scale Graphcited by 39
- 2020Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothingcited by 29
- 2019Popularity Prediction on Social Platforms with Coupled Graph Neural Networkscited by 26
- 2019Adversarial Training Methods for Network Embeddingcited by 26
- 2021Graph Sanitation with Application to Node Classificationcited by 20
- 2023Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networkscited by 16
- 2020Adversarial Immunization for Certifiable Robustness on Graphscited by 14
- 2022Projective Ranking-based GNN Evasion Attackscited by 14
- 2022Adversarial Camouflage for Node Injection Attack on Graphscited by 11
- 2021Adversarial Attack Framework on Graph Embedding Models with Limited Knowledgecited by 10
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.