An Effective Adversarial Defense Framework: From Robust Feature Perspective
Source abstract
Abstract
Deep neural networks are known to be vulnerable to adversarial attacks. Unfortunately, the underlying mechanisms remain insufficiently understood, leading to empirical defenses that often fail against new attacks. In this pap... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Anomaly Detection Techniques and Applications · Adversarial Robustness in Machine Learning
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (45)
Show source-provided references
1. LAFS: landmark-based facial self-supervised learning for face recognition
2. Planning-oriented autonomous driving
3. MFP: making full use of probability maps for interactive image segmentation
4. Szegedy C, Zaremba W, Sutskever I, Bruna J, Erhan D, Goodfellow I, et al. Intriguing properties of neural networks.arXiv:1312.6199. 2014.
5. Consistency and uncertainty: identifying unreliable responses from black-box vision-language models for selective visual question answering
6. Jacobian norm with selective input gradient regularization for interpretable adversarial defense10.1016/j.patcog.2023.109902 ↗
7. Certified adversarial robustness via randomized smoothing
8. Goodfellow IJ, Shlens J, Szegedy C. Explaining and harnessing adversarial examples. arXiv:1412.6572. 2015.
9. Fundamental limits on adversarial robustness
10. Exploring the space of adversarial images
11. Cubuk ED, Zoph B, Schoenholz SS, Le QV. Intriguing properties of adversarial examples. arXiv:1711.02846. 2018.
12. Adversarial examples are not bugs, they are features
13. Class-disentanglement and applications in adversarial detection and defense
14. Challenging common assumptions in the unsupervised learning of disentangled representations
15. Generative adversarial networks10.1145/3422622 ↗
16. BH2I-GAN: bidirectional hash_code-to-image translation using multi-generative multi-adversarial nets10.1016/j.patcog.2022.109010 ↗
17. beta-VAE: learning basic visual concepts with a constrained variational framework
18. Adversarial examples in the physical world
19. Ensemble adversarial training: attacks and defenses
20. Towards deep learning models resistant to adversarial attacks
21. Athalye · Proceedings of the 35th International Conference on Machine Learning (ICML) · 2018 · 80 · 284
22. Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks
23. Enhancing the transferability of adversarial attacks through variance tuning
24. A hamiltonian monte carlo method for probabilistic adversarial attack and learning10.1109/TPAMI.2020.3032061 ↗
25. Towards evaluating the robustness of neural networks
26. Generating adversarial examples for white-box attacks based on GAN
27. Pixle: a fast and effective black-box attack based on rearranging pixels
28. A query-efficient black-box adversarial attack via random search
29. Zhang · Advances in Neural Information Processing Systems 33 (NeurIPS 2019) · 2019 · 1829
30. Feature squeezing: detecting adversarial examples in deep neural networks
31. Countering adversarial images using input transformations
32. Defense against adversarial attacks using high-level representation guided denoiser
33. APE-GAN: adversarial perturbation elimination with GAN
34. Diffusion models for adversarial purification
35. Distillation as a defense to adversarial perturbations against deep neural networks
36. On the robustness of bayesian neural networks to adversarial attacks10.1109/TNNLS.2024.3386642 ↗
37. Robust principles: architectural design principles for adversarially robust CNNs
38. TRS: transferability reduced ensemble via promoting gradient diversity and model smoothness
39. Robustness via curvature regularization, and vice versa
40. Understanding adversarial examples from the mutual influence of images and perturbations
41. Kim H. Torchattacks: a pytorch repository for adversarial attacks. arXiv:2010.01950. 2020.
42. Gradient-based learning applied to document recognition10.1109/5.726791 ↗
43. Learning multiple layers of features from tiny images
44. Wide residual networks
45. Deep residual learning for image recognition