EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples

2018-02-08

Proceedings of the AAAI Conference on Artificial Intelligence, 32

Volume

Thirty-Second AAAI Conference on Artificial Intelligence 2018

AAAI Technical Track: Applications

Recent studies have highlighted the vulnerability of deep neural networks (DNNs) to adversarial examples — a visually indistinguishable adversarial image can easily be crafted to cause a well-trained model to misclassify. Existing methods for crafting adversarial examples are based on L2 and L∞ distortion metrics. However, despite the fact that L1 distortion accounts for the total variation and encourages sparsity in the perturbation, little has been developed for crafting L1-based adversarial examples. In this paper, we formulate the process of attacking DNNs via adversarial examples as an elastic-net regularized optimization problem. Our elastic-net attacks to DNNs (EAD) feature L1-oriented adversarial examples and include the state-of-the-art L2 attack as a special case. Experimental results on MNIST, CIFAR10 and ImageNet show that EAD can yield a distinct set of adversarial examples with small L1 distortion and attains similar attack performance to the state-of-the-art methods in different attack scenarios. More importantly, EAD leads to improved attack transferability and complements adversarial training for DNNs, suggesting novel insights on leveraging L1 distortion in adversarial machine learning and security implications of DNNs.

10.1609/aaai.v32i1.11302