Enhancing the Transferability of Adversarial Examples with Feature Transformation

Enhancing the Transferability of Adversarial Examples with Feature Transformation

The transferability of adversarial examples allows the attacker to fool deep neural networks (DNNs) without knowing any information about the target models. The current input transformation-based method generates adversarial examples by transforming the image in the input space, which implicitly int...

Full description

Bibliographic Details
Main Authors: Hao-Qi Xu, Cong Hu, He-Feng Yin
Format: Article
Language:English
Published: MDPI AG 2022-08-01
Series:Mathematics
Subjects:
adversarial example
feature transformation
black-box attack
ensemble attack
deep neural network
Online Access:https://www.mdpi.com/2227-7390/10/16/2976

Internet

https://www.mdpi.com/2227-7390/10/16/2976

Similar Items