Generating Adversarial Examples with Graph Neural Networks Article Swipe

MAKE IMPACT

Florian Jaeckle , Manish Kumar · YOU? · · 2021 · Open Access ·

Recent years have witnessed the deployment of adversarial attacks to evaluate the robustness of Neural Networks. Past work in this field has relied on traditional optimization algorithms that ignore the inherent structure of the problem and data, or generative methods that rely purely on learning and often fail to generate adversarial examples where they are hard to find. To alleviate these deficiencies, we propose a novel attack based on a graph neural network (GNN) that takes advantage of the strengths of both approaches; we call it AdvGNN. Our GNN architecture closely resembles the network we wish to attack. During inference, we perform forward-backward passes through the GNN layers to guide an iterative procedure towards adversarial examples. During training, its parameters are estimated via a loss function that encourages the efficient computation of adversarial examples over a time horizon. We show that our method beats state-of-the-art adversarial attacks, including PGD-attack, MI-FGSM, and Carlini and Wagner attack, reducing the time required to generate adversarial examples with small perturbation norms by over 65%. Moreover, AdvGNN achieves good generalization performance on unseen networks. Finally, we provide a new challenging dataset specifically designed to allow for a more illustrative comparison of adversarial attacks.

Type

article

Language

en

OA Status

green

Cited By

1

Related Works

20

OpenAlex ID

https://openalex.org/W3183386840

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W3183386840

Canonical identifier for this work in OpenAlex

Title

Generating Adversarial Examples with Graph Neural Networks

Work title

Type

article

OpenAlex work type

Language

en

Primary language

Publication year

2021

Year of publication

Publication date

2021-07-27

Full publication date if available

Authors

Florian Jaeckle, Manish Kumar

List of authors in order

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/abs/2105.14644

Direct OA link when available

Concepts

Adversarial system, Computer science, Artificial intelligence, Robustness (evolution), Generative grammar, Artificial neural network, Inference, Graph, Machine learning, Generalization, Computation, Deep neural networks, Theoretical computer science, Algorithm, Mathematics, Gene, Mathematical analysis, Chemistry, Biochemistry

Top concepts (fields/topics) attached by OpenAlex

Cited by

1

Total citation count in OpenAlex

Citations by year (recent)

2021: 1

Per-year citation counts (last 5 years)

Related works (count)

20

Other works algorithmically related by OpenAlex

Full payload