A new adversarial purification method that uses the forward and reverse processes of diffusion models to remove adversarial perturbations.
☆334Jan 29, 2023Updated 3 years ago
Alternatives and similar repositories for DiffPure
Users that are interested in DiffPure are comparing it to the libraries listed below
Sorting:
- ☆61Aug 9, 2023Updated 2 years ago
- Code for the paper "Better Diffusion Models Further Improve Adversarial Training" (ICML 2023)☆146Jul 31, 2023Updated 2 years ago
- RobustBench: a standardized adversarial robustness benchmark [NeurIPS 2021 Benchmarks and Datasets Track]☆770Mar 31, 2025Updated 11 months ago
- An unrestricted attack based on diffusion models that can achieve both good transferability and imperceptibility.☆256Nov 23, 2025Updated 3 months ago
- ☆23Jul 29, 2025Updated 7 months ago
- The code of the ICLR 2024 paper: Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization☆10Nov 21, 2024Updated last year
- Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"☆739May 16, 2024Updated last year
- [NeurIPS 2023] Codes for DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification☆39Feb 29, 2024Updated 2 years ago
- Code of paper [CVPR'24: Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?]☆23Apr 2, 2024Updated last year
- Implementation of "Adversarial purification with Score-based generative models", ICML 2021☆30Oct 24, 2021Updated 4 years ago
- [ICCV 2023 Oral] Official implementation of "Robust Evaluation of Diffusion-Based Adversarial Purification"☆25Dec 3, 2023Updated 2 years ago
- [NeurIPS'2023] Official Code Repo:Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability☆116Oct 31, 2023Updated 2 years ago
- Codes for NeurIPS 2020 paper "Adversarial Weight Perturbation Helps Robust Generalization"☆189Feb 18, 2021Updated 5 years ago
- Auto1111 port of NVlab's adversarial purification method that uses the forward and reverse processes of diffusion models to remove advers…☆13Aug 8, 2023Updated 2 years ago
- [BMVC 2023] Semantic Adversarial Attacks via Diffusion Models☆24Nov 30, 2023Updated 2 years ago
- Official repository for "On Generating Transferable Targeted Perturbations" (ICCV 2021)☆62Mar 25, 2023Updated 2 years ago
- Beyond imagenet attack (accepted by ICLR 2022) towards crafting adversarial examples for black-box domains.☆61Jun 15, 2022Updated 3 years ago
- Unofficial implementation of the DeepMind papers "Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples…☆98Mar 4, 2022Updated 3 years ago
- TRADES (TRadeoff-inspired Adversarial DEfense via Surrogate-loss minimization)☆553Mar 30, 2023Updated 2 years ago
- Official implementation of the CVPR 2022 paper "Backdoor Attacks on Self-Supervised Learning".☆76Oct 24, 2023Updated 2 years ago
- Code for our ICLR 2023 paper Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples.☆18May 31, 2023Updated 2 years ago
- Official code implement of Robust Classification via a Single Diffusion Model☆96Mar 7, 2025Updated 11 months ago
- Empirical tricks for training robust models (ICLR 2021)☆258May 25, 2023Updated 2 years ago
- ☆49Jun 19, 2024Updated last year
- PyTorch implementation of BPDA+EOT attack to evaluate adversarial defense with an EBM☆26Jun 30, 2020Updated 5 years ago
- Code for LAS-AT: Adversarial Training with Learnable Attack Strategy (CVPR2022)☆118Mar 30, 2022Updated 3 years ago
- PyTorch implementation of adversarial attacks [torchattacks]☆2,142Jun 29, 2024Updated last year
- Code for the paper "(De)Randomized Smoothing for Certifiable Defense against Patch Attacks" by Alexander Levine and Soheil Feizi.☆17Aug 22, 2022Updated 3 years ago
- The official code of IEEE S&P 2024 paper "Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferabili…☆20Aug 22, 2024Updated last year
- ☆15Dec 12, 2022Updated 3 years ago
- ECCV2024: Adversarial Prompt Tuning for Vision-Language Models☆31Nov 19, 2024Updated last year
- Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)☆33Dec 16, 2022Updated 3 years ago
- Code for ICLR2020 "Improving Adversarial Robustness Requires Revisiting Misclassified Examples"☆153Oct 15, 2020Updated 5 years ago
- ☆80Jul 23, 2024Updated last year
- ☆22Sep 13, 2021Updated 4 years ago
- ☆20Oct 5, 2023Updated 2 years ago
- Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Models☆266May 13, 2024Updated last year
- A list of papers in NeurIPS 2022 related to adversarial attack and defense / AI security.☆75Dec 5, 2022Updated 3 years ago
- A curated list of papers for the transferability of adversarial examples☆76Jul 8, 2024Updated last year