Deep Image Restoration Model: A Defense Method Against Adversarial Attacks
Source abstract
Abstract
These days, deep learning and computer vision are much-growing fields in this modern world of information technology. Deep learning algorithms and computer vision have achieved great success in different applications like image classification, speech recognition, self-driving vehicles, disease diagnostics, and many more. Despite success in various applications, it is found that these learning algorithms face severe threats due to adversarial attacks. Adversarial examples are inputs like images in the computer vision field, which are intentionally slightly changed or perturbed. These changes are humanly imperceptible. But are misclassified by a model with high probability and severely affects the performance or prediction. In this scenario, we present a deep image restoration model that restores adversarial examples so that the target model is classified correctly again. We proved that our defense method against adversarial attacks based on a deep image restoration model is simple and state-of-the-art by providing strong experimental results evidence. We have used MNIST and CIFAR10 datasets for experiments and analysis of our defense method. In the end, we have compared our method to other state-of-the-art defense methods and proved that our results are better than other rival methods.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Adversarial Robustness in Machine Learning · Integrated Circuits and Semiconductor Failure Analysis · Bacillus and Francisella bacterial research
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (30)
Show source-provided references
1. Deep learning10.1038/nature14539 ↗
2. A survey of practical adversarial example attacks
3. A survey on adversarial attacks and defences10.1049/cit2.12028 ↗
4. Adversarial attacks and defences competition
5. Adversarial attacks and defenses in deep learning10.1016/j.eng.2019.12.012 ↗
6. A. Constantin, E. Poll and J. Visser, “Adversarial examples-a complete characterisation of the phenomenon,” in arXiv preprint arXiv, 1810.01185, 2018.
7. R. R. Wiyatno, A. Xu, O. Dia, A. J. a. p. a. de Berker, “Adversarial examples in modern machine learning: A review,” in arXiv preprint arXiv, 1911.05268, 2019.
8. Adversarial examples: Opportunities and challenges
9. Threat of adversarial attacks on deep learning in computer vision: A survey10.1109/ACCESS.2018.2807385 ↗
10. C. Szegedy, W. Zaremba and D. Erhan, “Intriguing properties of neural networks,” in arXiv preprint arXiv 1312.6199, 2013.
11. I. Goodfellow, J. Shlens and C. Szegedy, “Explaining and harnessing adversarial examples,” in ArXiv Preprint ArXiv, 1412.6572, 2014.
12. Adversarial examples in the physical world10.1201/9781351251389-8 ↗
13. A. Madry and A. Makelov and L. Schmidt, “Towards deep learning models resistant to adversarial attacks,” in arXiv preprint arXiv, 1706.06083, 2017.
14. DeepFool: A simple and accurate method to fool deep neural networks
15. Towards evaluating the robustness of neural networks
16. Scale and rotation corrected cnns (src-cnns) for scale and rotation invariant character recognition
17. T. Florian, A. Kurakin and N. Papernot, “Ensemble adversarial training: Attacks and defenses,” in arXiv preprint arXiv:1705.0720, 2017.
18. Distillation as a defense to adversarial perturbations against deep neural networks
19. Magnet: A two-pronged defense against adversarial examples
20. P. Samangouei, M. Kabkab and R. Chellappa, “Defense-gan: Protecting classifiers against adversarial attacks using generative models,” in arXiv preprint arXiv, 1805.06605, 2018.
21. The defense of adversarial example with conditional generative adversarial networks
22. The mnist database of handwritten digit images for machine learning research10.1109/MSP.2012.2211477 ↗
23. R. Benjamin, R. Roelofs, L. Schmidt and V. Shankar, “Do cifar-10 classifiers generalise to cifar-10,” in ArXiv Preprint ArXiv:1806.00451, 2018.
24. I. Forrest, M. Moskewicz and S. Karayev, “Densenet: Implementing efficient convnet descriptor pyramids,” in ArXiv Preprint ArXiv:1404.1869, 2014.
25. Fd-mobilenet: improved mobilenet with a fast downsampling strategy
26. Gradient-based learning applied to document recognition10.1109/5.726791 ↗
27. Deep learning10.1038/nature14539 ↗
28. Identity mappings in deep residual networks
29. Developing deep into rectifiers: Surpassing human-level performance on imagenet classification
30. I. Goodfellow, P. Jean, M. Mirza, B. Xu, D. Warde-Farley et al., “Generative adversarial networks,” in arXiv preprint arXiv:1406.2661, 2014.