NVlabs / DiffPure
A new adversarial purification method that uses the forward and reverse processes of diffusion models to remove adversarial perturbations.
☆251Updated last year
Related projects: ⓘ
- Code for the paper "Better Diffusion Models Further Improve Adversarial Training" (ICML 2023)☆118Updated last year
- ☆46Updated last year
- An unrestricted attack based on diffusion models that can achieve both good transferability and imperceptibility.☆128Updated 2 weeks ago
- Certified robustness "for free" using off-the-shelf diffusion models and classifiers☆34Updated last year
- Official repo to reproduce the paper "How to Backdoor Diffusion Models?" published at CVPR 2023☆77Updated last week
- [NeurIPS'2023] Official Code Repo:Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability☆78Updated 10 months ago
- Code for our paper "Benchmarking the Robustness of Image Watermarks"☆41Updated this week
- ☆52Updated last year
- [ICCV 2023 Oral] Official implementation of "Robust Evaluation of Diffusion-Based Adversarial Purification"☆17Updated 9 months ago
- Official Pytorch repo of CVPR'23 and NeurIPS'23 papers on understanding replication in diffusion models.☆102Updated 9 months ago
- Code for the paper "Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models"☆37Updated 8 months ago
- ☆18Updated last month
- Unofficial implementation of the DeepMind papers "Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples…☆90Updated 2 years ago
- Implementation of "Adversarial purification with Score-based generative models", ICML 2021☆28Updated 2 years ago
- Code of the paper: A Recipe for Watermarking Diffusion Models☆116Updated 10 months ago
- ☆89Updated 5 months ago
- Code for the paper "On the Adversarial Robustness of Visual Transformers"☆55Updated 2 years ago
- ☆56Updated 8 months ago
- Library containing PyTorch implementations of various adversarial attacks and resources☆147Updated 4 months ago
- Official repository for "On Improving Adversarial Transferability of Vision Transformers" (ICLR 2022--Spotlight)☆69Updated last year
- ☆22Updated last month
- Code for LAS-AT: Adversarial Training with Learnable Attack Strategy (CVPR2022)☆105Updated 2 years ago
- This repository provides simple PyTorch implementations for adversarial training methods on CIFAR-10.☆151Updated 3 years ago
- A pytorch implementation of "Towards Deep Learning Models Resistant to Adversarial Attacks"☆144Updated 5 years ago
- Revisiting Transferable Adversarial Images (arXiv)☆113Updated last month
- ☆153Updated 3 years ago
- WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models (CVPR 2024)☆11Updated 3 months ago
- This repository contains the PyTorch implementation of Zeroth Order Optimization Based Adversarial Black Box Attack (https://arxiv.org/ab…☆37Updated last year
- Beyond imagenet attack (accepted by ICLR 2022) towards crafting adversarial examples for black-box domains.☆58Updated 2 years ago
- Attacks Which Do Not Kill Training Make Adversarial Learning Stronger (ICML2020 Paper)☆124Updated last year