Defending Against Image Corruptions Through Adversarial Augmentations

• URL: http://arxiv.org/abs/2104.01086v1
• Date: Fri, 2 Apr 2021 15:16:39 GMT
• Title: Defending Against Image Corruptions Through Adversarial Augmentations
• Authors: Dan A. Calian, Florian Stimberg, Olivia Wiles, Sylvestre-Alvise Rebuffi, Andras Gyorgy, Timothy Mann, Sven Gowal
• Abstract summary: Modern neural networks excel at image classification, yet they remain vulnerable to common image corruptions. Recent methods that focus on this problem, such as AugMix and DeepAugment, introduce defenses that operate in expectation over a distribution of image corruptions. We propose AdrialAugment, a technique which optimize the parameters of image-to-image models to generate adversarially corrupted augmented images.
• Score: 20.276628138912887
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern neural networks excel at image classification, yet they remain vulnerable to common image corruptions such as blur, speckle noise or fog. Recent methods that focus on this problem, such as AugMix and DeepAugment, introduce defenses that operate in expectation over a distribution of image corruptions. In contrast, the literature on $\ell_p$-norm bounded perturbations focuses on defenses against worst-case corruptions. In this work, we reconcile both approaches by proposing AdversarialAugment, a technique which optimizes the parameters of image-to-image models to generate adversarially corrupted augmented images. We theoretically motivate our method and give sufficient conditions for the consistency of its idealized version as well as that of DeepAugment. Our classifiers improve upon the state-of-the-art on common image corruption benchmarks conducted in expectation on CIFAR-10-C and improve worst-case performance against $\ell_p$-norm bounded perturbations on both CIFAR-10 and ImageNet.

Related papers

• Dynamic Batch Norm Statistics Update for Natural Robustness [5.366500153474747]
  We propose a unified framework consisting of a corruption-detection model and BN statistics update. Our results demonstrate about 8% and 4% accuracy improvement on CIFAR10-C and ImageNet-C.
  arXiv  Detail & Related papers  (2023-10-31T17:20:30Z)
• Frequency-Based Vulnerability Analysis of Deep Learning Models against Image Corruptions [48.34142457385199]
  We present MUFIA, an algorithm designed to identify the specific types of corruptions that can cause models to fail. We find that even state-of-the-art models trained to be robust against known common corruptions struggle against the low visibility-based corruptions crafted by MUFIA.
  arXiv  Detail & Related papers  (2023-06-12T15:19:13Z)
• Soft Diffusion: Score Matching for General Corruptions [84.26037497404195]
  We propose a new objective called Soft Score Matching that provably learns the score function for any linear corruption process. We show that our objective learns the gradient of the likelihood under suitable regularity conditions for the family of corruption processes. Our method achieves state-of-the-art FID score $1.85$ on CelebA-64, outperforming all previous linear diffusion models.
  arXiv  Detail & Related papers  (2022-09-12T17:45:03Z)
• Diffusion Models for Adversarial Purification [69.1882221038846]
  Adrial purification refers to a class of defense methods that remove adversarial perturbations using a generative model. We propose DiffPure that uses diffusion models for adversarial purification. Our method achieves the state-of-the-art results, outperforming current adversarial training and adversarial purification methods.
  arXiv  Detail & Related papers  (2022-05-16T06:03:00Z)
• Improving robustness against common corruptions with frequency biased models [112.65717928060195]
  unseen image corruptions can cause a surprisingly large drop in performance. Image corruption types have different characteristics in the frequency spectrum and would benefit from a targeted type of data augmentation. We propose a new regularization scheme that minimizes the total variation (TV) of convolution feature-maps to increase high-frequency robustness.
  arXiv  Detail & Related papers  (2021-03-30T10:44:50Z)
• On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness [78.6626755563546]
  Several new data augmentations have been proposed that significantly improve performance on ImageNet-C. We develop a new measure in this space between augmentations and corruptions called the Minimal Sample Distance to demonstrate there is a strong correlation between similarity and performance. We observe a significant degradation in corruption robustness when the test-time corruptions are sampled to be perceptually dissimilar from ImageNet-C. Our results suggest that test error can be improved by training on perceptually similar augmentations, and data augmentations may not generalize well beyond the existing benchmark.
  arXiv  Detail & Related papers  (2021-02-22T18:58:39Z)
• 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)
• A simple way to make neural networks robust against diverse image corruptions [29.225922892332342]
  We show that a simple but properly tuned training with additive Gaussian and Speckle noise generalizes surprisingly well to unseen corruptions. An adversarial training of the recognition model against uncorrelated worst-case noise leads to an additional increase in performance.
  arXiv  Detail & Related papers  (2020-01-16T20:10:25Z)

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.