Gradient-guided hierarchical feature attack for object detector

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...

Full beskrivning

Bibliografiska uppgifter
Huvudupphovsmän: Yang Wang, Yunfei Zheng, Lei Chen, Zhen Yang, Jingwei Wu, Tieyong Cao
Materialtyp: Artikel
Språk:English
Publicerad: Elsevier 2024-01-01
Serie:Journal of King Saud University: Computer and Information Sciences
Ämnen:
Adversarial attack
Attack transferability
Neural network robustness
Länkar:http://www.sciencedirect.com/science/article/pii/S131915782300455X

Internet

http://www.sciencedirect.com/science/article/pii/S131915782300455X

Liknande verk