mlsanityData to 7 Oct 2026

Towards Efficiently Evaluating the Robustness of Deep Neural Networks in IoT Systems: A GAN-based Method

arXiv 2111.10055 ↗First posted 19 Nov 2021cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Intelligent Internet of Things (IoT) systems based on deep neural networks (DNNs) have been widely deployed in the real world. However, DNNs are found to be vulnerable to adversarial examples, which raises people's concerns about intelligent IoT systems' reliability and security. Testing and evaluating the robustness of IoT systems becomes necessary and essential. Recently various attacks and strategies have been proposed, but the efficiency problem remains unsolved properly. Existing methods are either computationally extensive or time-consuming, which is not applicable in practice. In this paper, we propose a novel framework called Attack-Inspired GAN (AI-GAN) to generate adversarial examples conditionally. Once trained, it can generate adversarial perturbations efficiently given input images and target classes. We apply AI-GAN on different datasets in white-box settings, black-box settings and targeted models protected by state-of-the-art defenses. Through extensive experiments, AI-GAN achieves high attack success rates, outperforming existing methods, and reduces generation time significantly. Moreover, for the first time, AI-GAN successfully scales to complex datasets e.g. CIFAR-100 and ImageNet, with about 90% success rates among all classes.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 33 of its 53 references that are in the map. First posted on arXiv 19 Nov 2021.

Builds on

33 of 53 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2013Intriguing properties of neural networkscited by 5,114
  8. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  9. 2016Wide Residual Networkscited by 3,057
  10. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  11. 2017Improved Training of Wasserstein GANscited by 2,223
  12. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
21 more
  1. 2016Adversarial examples in the physical worldcited by 1,762
  2. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  3. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  4. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 806
  5. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  6. 2016Generative Adversarial Text to Image Synthesiscited by 735
  7. 2019Unified Language Model Pre-training for Natural Language Understanding and Generationcited by 668
  8. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  9. 2017Wasserstein GANcited by 635
  10. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 562
  11. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  12. 2018Feature Denoising for Improving Adversarial Robustnesscited by 312
  13. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 276
  14. 2018Generating Adversarial Examples with Adversarial Networkscited by 256
  15. 2018cGANs with Projection Discriminatorcited by 253
  16. 2017Generative Adversarial Perturbationscited by 153
  17. 2018Constructing Unrestricted Adversarial Examples with Generative Modelscited by 135
  18. 2017Adversarial Transformation Networks: Learning to Generate Adversarial Examplescited by 60
  19. 2015Massively Multitask Networks for Drug Discoverycited by 49
  20. 2018IoT Security Techniques Based on Machine Learningcited by 22
  21. 2020GAP++: Learning to generate target-conditioned adversarial examplescited by 5

Built on by

Not cited yet.