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


  • Pin-Yu Chen IBM Research AI
  • Yash Sharma The Cooper Union, New York
  • Huan Zhang University of California, Davis
  • Jinfeng Yi Tencent AI Lab
  • Cho-Jui Hsieh University of California, Davis




adversarial machine learning, elastic-net optimization, adversarial example, neural network, robustness


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.




How to Cite

Chen, P.-Y., Sharma, Y., Zhang, H., Yi, J., & Hsieh, C.-J. (2018). EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). https://doi.org/10.1609/aaai.v32i1.11302