Robin-WZQ / T2IShieldLinks
[ECCV'24] T2IShield: Defending Against Backdoors on Text-to-Image Diffusion Models
β16Updated 4 months ago
Alternatives and similar repositories for T2IShield
Users that are interested in T2IShield are comparing it to the libraries listed below
Sorting:
- π‘οΈ[ICLR'2024] Toward effective protection against diffusion-based mimicry through score distillation, a.k.a SDS-Attackβ56Updated last year
- [CVPR 2024] official code for SimACβ22Updated 9 months ago
- List of T2I safety papers, updated daily, welcome to discuss using Discussionsβ65Updated last year
- Code of paper [CVPR'24: Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?]β22Updated last year
- [CVPR'24 Oral] Metacloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learningβ29Updated 11 months ago
- β28Updated last year
- A collection of resources on attacks and defenses targeting text-to-image diffusion modelsβ75Updated 7 months ago
- AdvDiffuser: Natural Adversarial Example Synthesis with Diffusion Models (ICCV 2023)β19Updated 2 years ago
- [MM '24] EvilEdit: Backdooring Text-to-Image Diffusion Models in One Secondβ25Updated 11 months ago
- The official implementation of ECCV'24 paper "To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsβ¦β84Updated 8 months ago
- [NeurIPS 2023] Content-based Unrestricted Adversarial Attackβ28Updated 3 months ago
- β35Updated 9 months ago
- [MM'23 Oral] "Text-to-image diffusion models can be easily backdoored through multimodal data poisoning"β32Updated 2 months ago
- DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing (ICLR 2025)β35Updated 5 months ago
- EraseDiff: Erasing Data Influence in Diffusion Modelsβ12Updated 11 months ago
- This is the official repo of the paper "Latent Guard: a Safety Framework for Text-to-image Generation"β51Updated last year
- β30Updated last year
- β33Updated last year
- β58Updated 2 years ago
- Disrupting Diffusion: Token-Level Attention Erasure Attack against Diffusion-based Customization(ACM MM2024)β18Updated 6 months ago
- [CVPR2025] We present SleeperMark, a novel framework designed to embed resilient watermarks into T2I diffusion modelsβ30Updated 5 months ago
- Official implementation of NeurIPS'24 paper "Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Modelβ¦β49Updated 11 months ago
- [CVPR 2025] Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Modelsβ11Updated last month
- [CVPR23W] "A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion" by Haomin Zhuang, Yihua Zhang and Sijia Liuβ26Updated last year
- β27Updated 2 years ago
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdfβ21Updated last year
- BackdoorDM: A Comprehensive Benchmark for Backdoor Learning in Diffusion Modelβ17Updated 2 months ago
- Official implementation of "Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models"β24Updated 4 months ago
- Code Repo for the NeurIPS 2023 paper "VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models"β27Updated last month
- Official implement of paper: Stable Diffusion is Unstableβ23Updated last year