Adversarial Defense Technology for Small Infrared Targets
Source abstract
Abstract
With the rapid development of deep learning-based detection algorithms, deep learning is widely used in the field of infrared small target detection. However, well-designed adversarial samples can fool human visual perception... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Infrared Target Detection Methodologies · Advanced Measurement and Detection Methods · Advanced Semiconductor Detectors and Materials
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (36)
Show source-provided references
1. Intriguing properties of neural networks
2. Defending against universal perturbations with shared adversarial training
3. Towards deep neural network architectures robust to adversarial examples
4. R. Feinman, R. Ryan, S. S. Curtin, and A. B. Gardner, “Detecting adversarial samples from artifacts,” 2017. doi: 10.48550/arXiv.1703.00410.
5. Defense-GAN: Protecting classifiers against adversarial attacks using generative models
6. Collaborative Defense-GAN for protecting adversarial attacks on classification system10.1016/j.eswa.2022.118957 ↗
7. Learning perturbations for adversarial defense based on GAN structure10.1016/j.image.2022.116659 ↗
8. A self-supervised approach for adversarial robustness
9. Explaining and harnessing adversarial examples
10. DeepFool: A simple and accurate method to fool deep neural networks
11. Towards deep learning models resistant to adversarial attacks
12. Adversarial examples in the physical world10.1201/9781351251389-8 ↗
13. Boosting adversarial attacks with momentum
14. The limitations of deep learning in adversarial settings
15. Distillation as a defense to adversarial perturbations against deep neural networks
16. Towards evaluating the robustness of neural networks
17. Improving adversarial transferability via neuron attribution- based attacks
18. Query-efficient adversarial attack based on Latin hypercube sampling
19. Adversarial training for free!
20. Theoretically principled trade-off between robustness and accuracy
21. Training robust deep neural networks via adversarial noise propagation10.1109/TIP.2021.3082317 ↗
22. mixup: Beyond empirical risk minimization
23. Adversarial robustness of sparse local lipschitz predictors10.1137/22M1478835 ↗
24. Defense against adversarial attacks using high-level representation guided denoiser
25. Defense against adversarial images using web-scale nearest-neighbor search
26. Ape-gan: Adversarial perturbation elimination with gan
27. Evaluation of GAN-based model for adversarial training
28. CBAM: Convolutional block attention module
29. Infrared small target detection based on cascaded nested U-Net
30. Attentional local contrast networks for infrared small target detection10.1109/TGRS.2020.3044958 ↗
31. UIU-Net: U-Net in U-Net for infrared small object detection10.1109/TIP.2022.3228497 ↗
32. Dense nested attention network for infrared small target detection10.1109/TIP.2022.3199107 ↗
33. ZOO: Zeroth order optimization based black-box attacks to deep neural networks without training substitute models
34. Decision-based adversarial attacks: Reliable attacks against black-box machine learning models
35. Learn2Perturb: An end-to-end feature perturbation learning to improve adversarial robustness
36. Wang · Nov. 2019 · 8509