Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks
arXiv:1904.02884
Abstract
Deep neural networks are vulnerable to adversarial examples, which can mislead classifiers by adding imperceptible perturbations. An intriguing property of adversarial examples is their good transferability, making black-box attacks feasible in real-world applications. Due to the threat of adversarial attacks, many methods have been proposed to improve the robustness. Several state-of-the-art defenses are shown to be robust against transferable adversarial examples. In this paper, we propose a translation-invariant attack method to generate more transferable adversarial examples against the defense models. By optimizing a perturbation over an ensemble of translated images, the generated adversarial example is less sensitive to the white-box model being attacked and has better transferability. To improve the efficiency of attacks, we further show that our method can be implemented by convolving the gradient at the untranslated image with a pre-defined kernel. Our method is generally applicable to any gradient-based attack method. Extensive experiments on the ImageNet dataset validate the effectiveness of the proposed method. Our best attack fools eight state-of-the-art defenses at an 82% success rate on average based only on the transferability, demonstrating the insecurity of the current defense techniques.
arXiv commentCVPR 2019 (Oral)
References in corpus (15)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Explaining and Harnessing Adversarial Examples
- Intriguing properties of neural networks
- Ensemble Adversarial Training: Attacks and Defenses
- ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
- Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
- Synthesizing Robust Adversarial Examples
- Adversarial Machine Learning at Scale
- Robustness May Be at Odds with Accuracy
- Mitigating Adversarial Effects Through Randomization
- Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models
- Quantifying Translation-Invariance in Convolutional Neural Networks
- Boosting Adversarial Attacks with Momentum
- Max-Mahalanobis Linear Discriminant Analysis Networks
- Towards Robust Detection of Adversarial Examples