Improving Transferable Targeted Adversarial Attack for Object Detection Using RCEN Framework and Logit Loss Optimization
Source abstract
Abstract
Object detection finds wide application in various sectors, including autonomous driving, industry, and healthcare. Recent studies have highlighted the vulnerability of object detection models built using deep neural networks... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Adversarial Robustness in Machine Learning · Advanced Neural Network Applications · Brain Tumor Detection and Classification
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (37)
Show source-provided references
1. Survey on image object detection algorithms based on deep learning
2. Object detection with deep learning: A review10.1109/TNNLS.2018.2876865 ↗
3. Fully convolutional networks for semantic segmentation
4. Neural image caption generation with visual attention
5. Convolutional features for correlation filter based visual tracking
6. A mobile robotic arm grasping system with autonomous navigation and object detection
7. Review of artificial intelligence adversarial attack and defense technologies10.3390/app9050909 ↗
8. C. Szegedy et al., “Intriguing properties of neural networks,” 2013, arXiv:1312.6199.
9. Threat of adversarial attacks on deep learning in computer vision: A survey10.1109/ACCESS.2018.2807385 ↗
10. UAST: Uncertainty-aware siamese tracking
11. Towards universal and sparse adversarial examples for visual object tracking10.1016/j.asoc.2024.111252 ↗
12. A survey on adversarial attacks and defenses for object detection and their applications in autonomous vehicles10.1007/s00371-022-02660-6 ↗
13. A survey on transferability of adversarial examples across deep neural networks
14. N. Papernot, P. McDaniel, and I. Goodfellow, “Transferability in machine learning: From phenomena to black-box attacks using adversarial samples,” 2016, arXiv:1605.07277.
15. Adversarial examples on object recognition: A comprehensive survey10.1145/3398394 ↗
16. Explaining and harnessing adversarial examples
17. Towards deep learning models resistant to adversarial attacks
18. DeepFool: A simple and accurate method to fool deep neural networks
19. Towards evaluating the robustness of neural networks
20. Adversarial examples for semantic segmentation and object detection
21. Y. Li, D. Tian, M. Chang, X. Bian, and S. Lyu, “Robust adversarial perturbation on deep proposal-based models,” 2018, arXiv:1809.05962.
22. Adversarial objectness gradient attacks in real-time object detection systems
23. Transferable adversarial attacks for image and video object detection
24. Evading defenses to transferable adversarial examples by translation-invariant attacks
25. Boosting adversarial attacks with momentum
26. Nesterov accelerated gradient and scale invariance for adversarial attacks
27. Enhancing the transferability of adversarial attacks through variance tuning
28. Towards transferable targeted attack
29. Faster R-CNN: An approach to real-time object detection
30. Faster R-CNN: Towards real-time object detection with region proposal networks10.1109/TPAMI.2016.2577031 ↗
31. Mask R-CNN
32. J. Redmon and A. Farhadi, “YOLOv3: An incremental improvement,” 2018. Accessed: Mar. 15, 2024. [Online]. Available: http://personeltest.ru/aways/pjreddie.com/media/files/papers/YOLOv3.pdf
33. You only look once: Unified, real-time object detection
34. Inception single shot multibox detector for object detection
35. Focal loss for dense object detection
36. Admix: Enhancing the transferability of adversarial attacks
37. Contextual adversarial attacks for object detection