mlsanityData to 7 Oct 2026

Improving Transformation-based Defenses against Adversarial Examples with First-order Perturbations

arXiv 2103.04565 ↗First posted 8 Mar 2021cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep neural networks have been successfully applied in various machine learning tasks. However, studies show that neural networks are susceptible to adversarial attacks. This exposes a potential threat to neural network-based intelligent systems. We observe that the probability of the correct result outputted by the neural network increases by applying small first-order perturbations generated for non-predicted class labels to adversarial examples. Based on this observation, we propose a method for counteracting adversarial perturbations to improve adversarial robustness. In the proposed method, we randomly select a number of class labels and generate small first-order perturbations for these selected labels. The generated perturbations are added together and then clamped onto a specified space. The obtained perturbation is finally added to the adversarial example to counteract the adversarial perturbation contained in the example. The proposed method is applied at inference time and does not require retraining or finetuning the model. We experimentally validate the proposed method on CIFAR-10 and CIFAR-100. The results demonstrate that our method effectively improves the defense performance of several transformation-based defense methods, especially against strong adversarial examples generated using more iterations.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 35 references that are in the map. First posted on arXiv 8 Mar 2021.

Builds on

24 of 35 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2013Intriguing properties of neural networkscited by 5,114
  7. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  8. 2016Adversarial Machine Learning at Scalecited by 934
  9. 2017Countering Adversarial Images using Input Transformationscited by 517
  10. 2017Mitigating Adversarial Effects Through Randomizationcited by 382
  11. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
  12. 2019Towards Stable and Efficient Training of Verifiably Robust Neural Networkscited by 204
12 more
  1. 2020Boosting Adversarial Training with Hypersphere Embeddingcited by 97
  2. 2016Robustness of classifiers: from adversarial to random noisecited by 87
  3. 2018Adversarial vulnerability for any classifiercited by 78
  4. 2015Analysis of classifiers' robustness to adversarial perturbationscited by 76
  5. 2018Deflecting Adversarial Attacks with Pixel Deflectioncited by 71
  6. 2019Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attackscited by 54
  7. 2019Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracycited by 49
  8. 2019A New Defense Against Adversarial Images: Turning a Weakness into a Strengthcited by 49
  9. 2018Deep Defense: Training DNNs with Improved Adversarial Robustnesscited by 41
  10. 2015Exploring the Space of Adversarial Imagescited by 28
  11. 2018Max-Mahalanobis Linear Discriminant Analysis Networkscited by 18
  12. 2019Improving the Robustness of Deep Neural Networks via Adversarial Training with Triplet Losscited by 13

Built on by

Not cited yet.