IBM / BadDiffusion
Official repo to reproduce the paper "How to Backdoor Diffusion Models?" published at CVPR 2023
☆86Updated 6 months ago
Alternatives and similar repositories for BadDiffusion:
Users that are interested in BadDiffusion are comparing it to the libraries listed below
- Code Repo for the NeurIPS 2023 paper "VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models"☆23Updated 6 months ago
- ☆58Updated 2 years ago
- [NeurIPS 2023] Codes for DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification☆28Updated last year
- ☆23Updated last year
- This is the official implementation of our paper 'Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protecti…☆55Updated 11 months ago
- ☆25Updated 7 months ago
- ☆53Updated last year
- [NeurIPS'2023] Official Code Repo:Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability☆99Updated last year
- code of paper "IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Gene…☆26Updated 9 months ago
- A collection of resources on attacks and defenses targeting text-to-image diffusion models☆59Updated 2 months ago
- ☆65Updated last year
- [CVPR23W] "A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion" by Haomin Zhuang, Yihua Zhang and Sijia Liu☆26Updated 6 months ago
- ☆32Updated 5 months ago
- Universal Adversarial Perturbations (UAPs) for PyTorch☆48Updated 3 years ago
- ☆34Updated 2 years ago
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆54Updated 2 years ago
- AdvDiffuser: Natural Adversarial Example Synthesis with Diffusion Models (ICCV 2023)☆17Updated last year
- Divide-and-Conquer Attack: Harnessing the Power of LLM to Bypass the Censorship of Text-to-Image Generation Mode☆18Updated 3 weeks ago
- Code for the paper "Better Diffusion Models Further Improve Adversarial Training" (ICML 2023)☆136Updated last year
- [MM'23 Oral] "Text-to-image diffusion models can be easily backdoored through multimodal data poisoning"☆27Updated last week
- [ICLR2023] Distilling Cognitive Backdoor Patterns within an Image☆34Updated 4 months ago
- Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)☆33Updated 2 years ago
- Revisiting Transferable Adversarial Images (arXiv)☆120Updated this week
- Spectrum simulation attack (ECCV'2022 Oral) towards boosting the transferability of adversarial examples☆100Updated 2 years ago
- A Unified Approach to Interpreting and Boosting Adversarial Transferability (ICLR2021)☆29Updated 2 years ago
- Official implementation of the ICCV2023 paper: Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregatio…☆23Updated last year
- [CVPR 2023] The official implementation of our CVPR 2023 paper "Detecting Backdoors During the Inference Stage Based on Corruption Robust…☆21Updated last year
- Simple yet effective targeted transferable attack (NeurIPS 2021)☆48Updated 2 years ago
- This code is the official implementation of WEvade.☆38Updated last year
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf☆19Updated 11 months ago