NVlabs / DiffPure
A new adversarial purification method that uses the forward and reverse processes of diffusion models to remove adversarial perturbations.
☆277Updated last year
Alternatives and similar repositories for DiffPure:
Users that are interested in DiffPure are comparing it to the libraries listed below
- Code for the paper "Better Diffusion Models Further Improve Adversarial Training" (ICML 2023)☆132Updated last year
- ☆53Updated last year
- Official repo to reproduce the paper "How to Backdoor Diffusion Models?" published at CVPR 2023☆85Updated 4 months ago
- An unrestricted attack based on diffusion models that can achieve both good transferability and imperceptibility.☆171Updated 3 months ago
- Certified robustness "for free" using off-the-shelf diffusion models and classifiers☆36Updated last year
- [NeurIPS'2023] Official Code Repo:Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability☆94Updated last year
- ☆56Updated 2 years ago
- [ICCV 2023 Oral] Official implementation of "Robust Evaluation of Diffusion-Based Adversarial Purification"☆23Updated last year
- ☆29Updated 3 months ago
- Official code implement of Robust Classification via a Single Diffusion Model☆67Updated 8 months ago
- [NeurIPS 2024 D&B Track] UnlearnCanvas: A Stylized Image Dataset to Benchmark Machine Unlearning for Diffusion Models by Yihua Zhang, Cho…☆61Updated 2 months ago
- ☆25Updated 5 months ago
- Code for LAS-AT: Adversarial Training with Learnable Attack Strategy (CVPR2022)☆114Updated 2 years ago
- The official implementation of ECCV'24 paper "To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Uns…☆64Updated 2 months ago
- Official Pytorch repo of CVPR'23 and NeurIPS'23 papers on understanding replication in diffusion models.☆105Updated last year
- Revisiting Transferable Adversarial Images (arXiv)☆118Updated 3 months ago
- ☆100Updated 9 months ago
- Square Attack: a query-efficient black-box adversarial attack via random search [ECCV 2020]☆152Updated 4 years ago
- Fantastic Robustness Measures: The Secrets of Robust Generalization [NeurIPS 2023]☆33Updated last week
- A pytorch implementation of "Towards Deep Learning Models Resistant to Adversarial Attacks"☆149Updated 5 years ago
- Implementation of "Adversarial purification with Score-based generative models", ICML 2021☆28Updated 3 years ago
- A collection of resources on attacks and defenses targeting text-to-image diffusion models☆53Updated last week
- 🛡️[ICLR'2024] Toward effective protection against diffusion-based mimicry through score distillation, a.k.a SDS-Attack☆40Updated 9 months ago
- Code for our paper "Benchmarking the Robustness of Image Watermarks"☆61Updated 4 months ago
- Code of the paper: A Recipe for Watermarking Diffusion Models☆135Updated 2 months ago
- RobustBench: a standardized adversarial robustness benchmark [NeurIPS 2021 Benchmarks and Datasets Track]☆689Updated 3 weeks ago
- Spectrum simulation attack (ECCV'2022 Oral) towards boosting the transferability of adversarial examples☆98Updated 2 years ago
- [NeurIPS 2023] Codes for DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification☆25Updated 10 months ago
- [NeurIPS 2023] Code for the paper "Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threa…☆38Updated last month
- The code for the paper titled as "DifAttack: Query-Efficient Black-Box Attack via Disentangled Feature Space".☆15Updated 7 months ago