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…
☆48Updated 11 months ago
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…☆83Updated 7 months ago
- ☆35Updated 8 months ago
- [NeurIPS 2024 D&B Track] UnlearnCanvas: A Stylized Image Dataset to Benchmark Machine Unlearning for Diffusion Models by Yihua Zhang, Cho…☆74Updated 10 months ago
- [CVPR'24 Oral] Metacloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning☆29Updated 10 months ago
- 🛡️[ICLR'2024] Toward effective protection against diffusion-based mimicry through score distillation, a.k.a SDS-Attack☆56Updated last year
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf☆21Updated last year
- [ICML 2024] Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts (Official Pytorch Implementati…☆46Updated 10 months ago
- ☆58Updated 2 years ago
- ☆21Updated 2 years ago
- A collection of resources on attacks and defenses targeting text-to-image diffusion models☆73Updated 6 months ago
- [MM '24] EvilEdit: Backdooring Text-to-Image Diffusion Models in One Second☆24Updated 10 months ago
- [ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation…☆132Updated 4 months ago
- PDM-based Purifier☆22Updated 11 months ago
- ☆64Updated last year
- ☆33Updated last year
- [ECCV-2024] Transferable Targeted Adversarial Attack, CLIP models, Generative adversarial network, Multi-target attacks☆36Updated 5 months ago
- List of T2I safety papers, updated daily, welcome to discuss using Discussions☆64Updated last year
- Code of paper [CVPR'24: Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?]☆22Updated last year
- Official repo for An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization☆15Updated last year
- [CVPR 2024] official code for SimAC☆20Updated 8 months ago
- ☆28Updated last year
- ☆15Updated 6 months ago
- [ECCV 2024] "Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers" (Official Implementation)☆40Updated 7 months ago
- [ICML 2025] X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP☆30Updated 3 months ago
- [ICCV-2025] Universal Adversarial Attack, Multimodal Adversarial Attacks, VLP models, Contrastive Learning, Cross-modal Perturbation Gene…☆25Updated 2 months ago
- [CVPR 2024] Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers☆16Updated 11 months ago
- ☆38Updated last year
- [BMVC 2023] Semantic Adversarial Attacks via Diffusion Models☆21Updated last year
- ☆19Updated 2 years ago
- Official implement of paper: Stable Diffusion is Unstable☆23Updated last year