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…
☆49Updated 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…☆84Updated 7 months ago
- ☆35Updated 9 months ago
- [NeurIPS 2024 D&B Track] UnlearnCanvas: A Stylized Image Dataset to Benchmark Machine Unlearning for Diffusion Models by Yihua Zhang, Cho…☆77Updated 11 months ago
- [CVPR'24 Oral] Metacloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning☆29Updated 11 months ago
- 🛡️[ICLR'2024] Toward effective protection against diffusion-based mimicry through score distillation, a.k.a SDS-Attack☆56Updated last year
- ☆21Updated 2 years ago
- [ICML 2024] Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts (Official Pytorch Implementati…☆48Updated 11 months ago
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf☆21Updated last year
- A collection of resources on attacks and defenses targeting text-to-image diffusion models☆75Updated 7 months ago
- List of T2I safety papers, updated daily, welcome to discuss using Discussions☆65Updated last year
- ☆15Updated 7 months ago
- ☆64Updated last year
- ☆28Updated last year
- [ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation…☆137Updated 5 months ago
- ☆30Updated 6 months ago
- ☆58Updated 2 years ago
- [CVPR 2024] official code for SimAC☆22Updated 9 months ago
- PDM-based Purifier☆22Updated 11 months ago
- ☆33Updated last year
- [ECCV-2024] Transferable Targeted Adversarial Attack, CLIP models, Generative adversarial network, Multi-target attacks☆37Updated 6 months ago
- Code of paper [CVPR'24: Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?]☆22Updated last year
- [MM '24] EvilEdit: Backdooring Text-to-Image Diffusion Models in One Second☆25Updated 11 months ago
- Code for the paper "Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks"☆36Updated last year
- The official implementation of the paper "Towards Safe Self-Distillation of Internet-Scale Text-to-Image Diffusion Models" (ICML 2023 Wor…☆21Updated last year
- ☆38Updated last year
- [ECCV 2024] "Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers" (Official Implementation)☆41Updated 7 months ago
- Official repo for An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization☆16Updated last year
- [CVPR 2024] Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation☆46Updated last year
- Investigating and Defending Shortcut Learning in Personalized Diffusion Models☆12Updated 11 months ago
- DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing (ICLR 2025)☆35Updated 5 months ago