OPTML-Group / AdvUnlearn
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…
☆39Updated 4 months ago
Alternatives and similar repositories for AdvUnlearn:
Users that are interested in AdvUnlearn are comparing it to the libraries listed below
- [CVPR'24 Oral] Metacloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning☆21Updated 4 months ago
- The official implementation of ECCV'24 paper "To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Uns…☆71Updated 2 weeks ago
- [NeurIPS 2024 D&B Track] UnlearnCanvas: A Stylized Image Dataset to Benchmark Machine Unlearning for Diffusion Models by Yihua Zhang, Cho…☆64Updated 4 months ago
- A collection of resources on attacks and defenses targeting text-to-image diffusion models☆60Updated 2 months ago
- ☆27Updated 2 months ago
- ☆31Updated 8 months ago
- ☆12Updated 3 weeks ago
- ☆26Updated 3 months ago
- ☆60Updated 5 months ago
- ☆19Updated 6 months ago
- List of T2I safety papers, updated daily, welcome to discuss using Discussions☆57Updated 7 months ago
- ☆17Updated last year
- Code of paper [CVPR'24: Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?]☆15Updated 11 months ago
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf☆19Updated 11 months ago
- This is a collection of awesome papers I have read (carefully or roughly) in the fields of security in diffusion models. Any suggestions …☆24Updated 4 months ago
- ☆13Updated 8 months ago
- ☆25Updated 7 months ago
- ☆40Updated last year
- 🛡️[ICLR'2024] Toward effective protection against diffusion-based mimicry through score distillation, a.k.a SDS-Attack☆43Updated 11 months ago
- [MM '24] EvilEdit: Backdooring Text-to-Image Diffusion Models in One Second☆14Updated 4 months ago
- ☆26Updated 9 months ago
- [CVPR 2024] official code for SimAC☆16Updated last month
- ☆12Updated 3 months ago
- [ECCV-2024] Transferable Targeted Adversarial Attack, CLIP models, Generative adversarial network, Multi-target attacks☆31Updated 7 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
- ☆58Updated 2 years ago
- [CVPR23W] "A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion" by Haomin Zhuang, Yihua Zhang and Sijia Liu☆26Updated 6 months ago
- [CVPR 2024] Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers☆17Updated 4 months ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images☆30Updated last year