NVlabs / DiffPure
A new adversarial purification method that uses the forward and reverse processes of diffusion models to remove adversarial perturbations.
☆267Updated last year
Related projects ⓘ
Alternatives and complementary repositories for DiffPure
- Code for the paper "Better Diffusion Models Further Improve Adversarial Training" (ICML 2023)☆125Updated last year
- ☆47Updated last year
- An unrestricted attack based on diffusion models that can achieve both good transferability and imperceptibility.☆151Updated last month
- Certified robustness "for free" using off-the-shelf diffusion models and classifiers☆36Updated last year
- Official repo to reproduce the paper "How to Backdoor Diffusion Models?" published at CVPR 2023☆82Updated 2 months ago
- [NeurIPS'2023] Official Code Repo:Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability☆87Updated last year
- ☆54Updated last year
- [ICCV 2023 Oral] Official implementation of "Robust Evaluation of Diffusion-Based Adversarial Purification"☆19Updated 11 months ago
- Code for our paper "Benchmarking the Robustness of Image Watermarks"☆54Updated 2 months ago
- Official code implement of Robust Classification via a Single Diffusion Model☆60Updated 6 months ago
- The official implementation of ECCV'24 paper "To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Uns…☆58Updated 2 weeks ago
- ☆57Updated 11 months ago
- ☆26Updated last month
- Unofficial implementation of the DeepMind papers "Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples…☆92Updated 2 years ago
- Library containing PyTorch implementations of various adversarial attacks and resources☆149Updated last month
- A pytorch implementation of "Towards Deep Learning Models Resistant to Adversarial Attacks"☆146Updated 5 years ago
- ☆98Updated 7 months ago
- This repository provides simple PyTorch implementations for adversarial training methods on CIFAR-10.☆157Updated 3 years ago
- Code for LAS-AT: Adversarial Training with Learnable Attack Strategy (CVPR2022)☆107Updated 2 years ago
- [NeurIPS 2023] Code for the paper "Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threa…☆38Updated 10 months ago
- ☆24Updated 3 months ago
- [NeurIPS 2024 D&B Track] UnlearnCanvas: A Stylized Image Dataset to Benchmark Machine Unlearning for Diffusion Models by Yihua Zhang, Cho…☆55Updated last week
- Spectrum simulation attack (ECCV'2022 Oral) towards boosting the transferability of adversarial examples☆90Updated 2 years ago
- RobustBench: a standardized adversarial robustness benchmark [NeurIPS 2021 Benchmarks and Datasets Track]☆669Updated 2 weeks ago
- Implementation of "Adversarial purification with Score-based generative models", ICML 2021☆28Updated 3 years ago
- Official Pytorch repo of CVPR'23 and NeurIPS'23 papers on understanding replication in diffusion models.☆104Updated 11 months ago
- Code of the paper: A Recipe for Watermarking Diffusion Models☆130Updated last week
- AdvDiffuser: Natural Adversarial Example Synthesis with Diffusion Models (ICCV 2023)☆16Updated last year
- Square Attack: a query-efficient black-box adversarial attack via random search [ECCV 2020]☆150Updated 4 years ago
- Empirical tricks for training robust models (ICLR 2021)☆250Updated last year