Adversarial Training against Location-Optimized Adversarial Patches

• URL: http://arxiv.org/abs/2005.02313v2
• Date: Mon, 14 Dec 2020 08:00:26 GMT
• Title: Adversarial Training against Location-Optimized Adversarial Patches
• Authors: Sukrut Rao, David Stutz, Bernt Schiele
• Abstract summary: adversarial patches: clearly visible, but adversarially crafted rectangular patches in images. We first devise a practical approach to obtain adversarial patches while actively optimizing their location within the image. We apply adversarial training on these location-optimized adversarial patches and demonstrate significantly improved robustness on CIFAR10 and GTSRB.
• Score: 84.96938953835249
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks have been shown to be susceptible to adversarial examples -- small, imperceptible changes constructed to cause mis-classification in otherwise highly accurate image classifiers. As a practical alternative, recent work proposed so-called adversarial patches: clearly visible, but adversarially crafted rectangular patches in images. These patches can easily be printed and applied in the physical world. While defenses against imperceptible adversarial examples have been studied extensively, robustness against adversarial patches is poorly understood. In this work, we first devise a practical approach to obtain adversarial patches while actively optimizing their location within the image. Then, we apply adversarial training on these location-optimized adversarial patches and demonstrate significantly improved robustness on CIFAR10 and GTSRB. Additionally, in contrast to adversarial training on imperceptible adversarial examples, our adversarial patch training does not reduce accuracy.

Related papers

• Defending Adversarial Patches via Joint Region Localizing and Inpainting [16.226410937026685]
  A series of experiments versus traffic sign classification and detection tasks are conducted to defend against various adversarial patch attacks. We propose a novel defense method based on a localizing and inpainting" mechanism to pre-process the input examples.
  arXiv  Detail & Related papers  (2023-07-26T15:11:51Z)
• The Enemy of My Enemy is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training [72.39526433794707]
  Adversarial training and its variants have been shown to be the most effective approaches to defend against adversarial examples. We propose a novel adversarial training scheme that encourages the model to produce similar outputs for an adversarial example and its inverse adversarial'' counterpart. Our training method achieves state-of-the-art robustness as well as natural accuracy.
  arXiv  Detail & Related papers  (2022-11-01T15:24:26Z)
• Collaborative Adversarial Training [82.25340762659991]
  We show that some collaborative examples, nearly perceptually indistinguishable from both adversarial and benign examples, can be utilized to enhance adversarial training. A novel method called collaborative adversarial training (CoAT) is thus proposed to achieve new state-of-the-arts.
  arXiv  Detail & Related papers  (2022-05-23T09:41:41Z)
• Inconspicuous Adversarial Patches for Fooling Image Recognition Systems on Mobile Devices [8.437172062224034]
  A variant of adversarial examples, called adversarial patch, draws researchers' attention due to its strong attack abilities. We propose an approach to generate adversarial patches with one single image. Our approach shows the strong attack abilities in white-box settings and the excellent transferability in black-box settings.
  arXiv  Detail & Related papers  (2021-06-29T09:39:34Z)
• Towards Defending against Adversarial Examples via Attack-Invariant Features [147.85346057241605]
  Deep neural networks (DNNs) are vulnerable to adversarial noise. adversarial robustness can be improved by exploiting adversarial examples. Models trained on seen types of adversarial examples generally cannot generalize well to unseen types of adversarial examples.
  arXiv  Detail & Related papers  (2021-06-09T12:49:54Z)
• Error Diffusion Halftoning Against Adversarial Examples [85.11649974840758]
  Adversarial examples contain carefully crafted perturbations that can fool deep neural networks into making wrong predictions. We propose a new image transformation defense based on error diffusion halftoning, and combine it with adversarial training to defend against adversarial examples.
  arXiv  Detail & Related papers  (2021-01-23T07:55:02Z)
• Robustness Out of the Box: Compositional Representations Naturally Defend Against Black-Box Patch Attacks [11.429509031463892]
  Patch-based adversarial attacks introduce a perceptible but localized change to the input that induces misclassification. In this work, we study two different approaches for defending against black-box patch attacks. We find that adversarial training has limited effectiveness against state-of-the-art location-optimized patch attacks.
  arXiv  Detail & Related papers  (2020-12-01T15:04:23Z)
• Generating Adversarial yet Inconspicuous Patches with a Single Image [15.217367754000913]
  We propose an approach to gen-erate adversarial yet inconspicuous patches with onesingle image. In our approach, adversarial patches areproduced in a coarse-to-fine way with multiple scalesof generators and discriminators. Our ap-proach shows strong attacking ability in both the white-box and black-box setting.
  arXiv  Detail & Related papers  (2020-09-21T11:56:01Z)
• Towards Achieving Adversarial Robustness by Enforcing Feature Consistency Across Bit Planes [51.31334977346847]
  We train networks to form coarse impressions based on the information in higher bit planes, and use the lower bit planes only to refine their prediction. We demonstrate that, by imposing consistency on the representations learned across differently quantized images, the adversarial robustness of networks improves significantly.
  arXiv  Detail & Related papers  (2020-04-01T09:31:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.