TransferAttack is a pytorch framework to boost the adversarial transferability for image classification.
Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)
Code for "CloudLeak: Large-Scale Deep Learning Models Stealing Through Adversarial Examples" (NDSS 2020)
[CVPR 2023] Official implementation of the Clean Feature Mixup (CFM) method
The official code of IEEE S&P 2024 paper "Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability". We study how to train surrogates model for boosting transfer attack.
Official code for "PubDef: Defending Against Transfer Attacks From Public Models" (ICLR 2024)
Add a description, image, and links to the transfer-attack topic page so that developers can more easily learn about it.
To associate your repository with the transfer-attack topic, visit your repo's landing page and select "manage topics."