The extension of "Patch-wise Attack for Fooling Deep Neural Network (ECCV2020)", and we aim to boost the success rates of targeted attack.
-
Updated
Mar 14, 2022 - Python
The extension of "Patch-wise Attack for Fooling Deep Neural Network (ECCV2020)", and we aim to boost the success rates of targeted attack.
(ECCV2024) Any Target Can be Offense: Adversarial Example Generation via Generalized Latent Infection
Attack models that are pretrained on ImageNet. (1) Attack single model or multiple models. (2) Apply white-box attacks or black-box attacks. (3) Apply non-targeted attacks or targeted attacks.
A Python sample for demonstrating Targeted Adversarial Attack - manipulate a source image to be classified as a specified target class by the machine learning classifier
Add a description, image, and links to the targeted-adversarial-attacks topic page so that developers can more easily learn about it.
To associate your repository with the targeted-adversarial-attacks topic, visit your repo's landing page and select "manage topics."