OPTML-Group / AdvUnlearnLinks
Official implementation of NeurIPS'24 paper "Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models". This work adversarially unlearns the text encoder to enhance the robustness of unlearned DMs against adversarial prompt attacks and achieves a better balance between unlearning performance and image generat…
☆50Updated last year
Alternatives and similar repositories for AdvUnlearn
Users that are interested in AdvUnlearn are comparing it to the libraries listed below
Sorting:
- The official implementation of ECCV'24 paper "To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Uns…☆87Updated 9 months ago
- ☆38Updated 11 months ago
- [CVPR'24 Oral] Metacloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning☆29Updated last year
- [NeurIPS 2024 D&B Track] UnlearnCanvas: A Stylized Image Dataset to Benchmark Machine Unlearning for Diffusion Models by Yihua Zhang, Cho…☆80Updated last year
- ☆23Updated 2 years ago
- [ICML 2024] Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts (Official Pytorch Implementati…☆52Updated last year
- 🛡️[ICLR'2024] Toward effective protection against diffusion-based mimicry through score distillation, a.k.a SDS-Attack☆59Updated last year
- A collection of resources on attacks and defenses targeting text-to-image diffusion models☆85Updated 8 months ago
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf☆24Updated last year
- [ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation…☆141Updated 6 months ago
- ☆42Updated last year
- ☆65Updated last year
- Code of paper [CVPR'24: Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?]☆23Updated last year
- [CVPR 2024] official code for SimAC☆22Updated 10 months ago
- List of T2I safety papers, updated daily, welcome to discuss using Discussions☆67Updated last year
- ☆59Updated 3 years ago
- [MM '24] EvilEdit: Backdooring Text-to-Image Diffusion Models in One Second☆26Updated last year
- ☆28Updated last year
- ☆35Updated last year
- [SatML 2024] Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk☆15Updated 9 months ago
- ☆39Updated 2 years ago
- PDM-based Purifier☆22Updated last year
- [CVPR'25]Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks☆26Updated 6 months ago
- [ICML 2025] X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP☆32Updated 6 months ago
- ☆33Updated 8 months ago
- ☆28Updated 2 years ago
- Official repo to reproduce the paper "How to Backdoor Diffusion Models?" published at CVPR 2023☆94Updated 3 months ago
- The official implementation of the paper "Towards Safe Self-Distillation of Internet-Scale Text-to-Image Diffusion Models" (ICML 2023 Wor…☆22Updated last year
- DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing (ICLR 2025)☆42Updated 7 months ago
- [CVPR 2024] Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers☆16Updated last year