2019 · 394 citations · 19 references
ComputingComputer ScienceComputer SecurityEdge ComputingMachine LearningDeep LearningGraph AlgorithmsGraph AnalyticsGraph MiningGraph-based LearningAdversarial Attack DetectionAdversarial ExamplesAdversarial RobustnessConvolutional Neural NetworksGradient ProgrammingGraph Convolutional NetworksGraph Neural NetworksPotential Perturbation
Graph deep learning models such as GCN achieve state‑of‑the‑art performance but, like other deep learning models, are vulnerable to adversarial attacks, and the discrete nature of graph connections and features creates unique challenges and opportunities for such attacks. This work proposes both an adversarial attack and a defense strategy for graph data. The attack and defense rely on integrated‑gradient analysis to accurately assess the impact of modifying discrete features or edges, enabling targeted perturbations and detection/recovery of adversarial changes. Targeted attacks produce statistically distinguishable graphs, and experiments on multiple datasets demonstrate the effectiveness of the proposed attack and defense methods.
Graph deep learning models, such as graph convolutional networks (GCN) achieve state-of-the-art performance for tasks on graph data. However, similar to other deep learning models, graph deep learning models are susceptible to adversarial attacks. However, compared with non-graph data the discrete nature of the graph connections and features provide unique challenges and opportunities for adversarial attacks and defenses. In this paper, we propose techniques for both an adversarial attack and a defense against adversarial attacks. Firstly, we show that the problem of discrete graph connections and the discrete features of common datasets can be handled by using the integrated gradient technique that accurately determines the effect of changing selected features or edges while still benefiting from parallel computations. In addition, we show that an adversarially manipulated graph using a targeted attack statistically differs from un-manipulated graphs. Based on this observation, we propose a defense approach which can detect and recover a potential adversarial perturbation. Our experiments on a number of datasets show the effectiveness of the proposed techniques.
19
Guillem Cucurull, Arantxa Casanova, Adriana Romero et al. · arXiv (Cornell University) · 2017 · 8.3K citations · Full text
Explaining and Harnessing Adversarial Examples
Ian Goodfellow, Jonathon Shlens, Christian Szegedy · arXiv (Cornell University) · 2014 · 8.2K citations · Full text
The Limitations of Deep Learning in Adversarial Settings
Nicolas Papernot, Patrick McDaniel, Somesh Jha et al. · 2016 · 3.9K citations
Spectral Networks and Locally Connected Networks on Graphs
Joan Bruna, Wojciech Zaremba, Arthur Szlam et al. · arXiv (Cornell University) · 2013 · 2.7K citations · Full text