Code for the paper Boosting Accuracy and Robustness of Student Models via Adaptive Adversarial Distillation (CVPR 2023).

Code for our paper "Building Robust Ensembles via Margin Boosting" (ICML 2022)

Empirical tricks for training robust models (ICLR 2021)

TRADES (TRadeoff-inspired Adversarial DEfense via Surrogate-loss minimization)

TransferAttack is a pytorch framework to boost the adversarial transferability for image classification.

Beyond imagenet attack (accepted by ICLR 2022) towards crafting adversarial examples for black-box domains.

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 tra…

An unofficial implementation of the paper《Towards Understanding and Boosting Adversarial Transferability from a Distribution Perspective》

EasyRobust: an Easy-to-use library for state-of-the-art Robust Computer Vision Research with PyTorch.

[NeurIPS 2023] Boosting Adversarial Transferability by Achieving Flat Local Maxima

Code for our ICLR 2023 paper Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples.

Spectrum simulation attack (ECCV'2022 Oral) towards boosting the transferability of adversarial examples

Repository for patch attacks against autonomous driving vision tasks.

An adversarial attack on object detectors