Gradient-guided hierarchical feature attack for object detector
Deep neural networks (DNNs) are vulnerable to adversarial attacks, which can cause security risks in computer information systems. Feature disruption attacks, as a typical form of adversarial attack, optimize adversarial examples by disrupting the intermediate features extracted by DNN. The existing...
Huvudupphovsmän: | , , , , , |
---|---|
Materialtyp: | Artikel |
Språk: | English |
Publicerad: |
Elsevier
2024-01-01
|
Serie: | Journal of King Saud University: Computer and Information Sciences |
Ämnen: | |
Länkar: | http://www.sciencedirect.com/science/article/pii/S131915782300455X |