Popular GitHub Repositories for Adversarial Robustness

RobustBench: a standardized adversarial robustness benchmark [NeurIPS 2021 Benchmarks and Datasets Track]

Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"

A Python library for adversarial machine learning focusing on benchmarking adversarial robustness.

alpha-beta-CROWN: An Efficient, Scalable and GPU Accelerated Neural Network Verifier (winner of VNN-COMP 2021, 2022, 2023, and 2024)

Square Attack: a query-efficient black-box adversarial attack via random search [ECCV 2020]

[CVPR 2022] "Aug-NeRF: Training Stronger Neural Radiance Fields with Triple-Level Physically-Grounded Augmentations" by Tianlong Chen*, Peihao Wang*, Zhiwen Fan, Zhangyang Wang

[ICLR 2021] "InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective" by Boxin Wang, Shuohang Wang, Yu Cheng, Zhe Gan, Ruoxi Jia, Bo Li, Jingjing Liu

Feature Scattering Adversarial Training (NeurIPS19)

Fantastic Robustness Measures: The Secrets of Robust Generalization [NeurIPS 2023]

Implementing the algorithm from our paper: "A Reputation Mechanism Is All You Need: Collaborative Fairness and Adversarial Robustness in Federated Learning".

Code for FAB-attack

Helper-based Adversarial Training: Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off

[ICLR 2020] ”Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference“

Adversarial Attack and Defense in Deep Ranking, T-PAMI, 2024

LAFEAT: Piercing Through Adversarial Defenses with Latent Features (CVPR 2021 Oral)

[CVPRW'22] A privacy attack that exploits Adversarial Training models to compromise the privacy of Federated Learning systems.

Imbalanced Gradients: A New Cause of Overestimated Adversarial Robustness. (MD attacks)

Code for the paper "Confidence-aware Denoised Fine-tuning of Off-the-shelf Models for Certified Robustness" (TMLR 2024)

[ICML 2021 Long Talk] "Sparse and Imperceptible Adversarial Attack via a Homotopy Algorithm" by Mingkang Zhu, Tianlong Chen, Zhangyang Wang

[TMLR 2023] as a featured article (spotlight :star2: or top 0.01% of the accepted papers). In this study, we systematically examine the robustness of both traditional and learned perceptual similarity metrics to imperceptible adversarial perturbations.