AAAAAAsuka / Impress
code of paper "IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI"
☆22Updated 6 months ago
Related projects ⓘ
Alternatives and complementary repositories for Impress
- ☆24Updated 3 months ago
- Official repo to reproduce the paper "How to Backdoor Diffusion Models?" published at CVPR 2023☆82Updated 2 months ago
- ☆15Updated 7 months ago
- [MM'23 Oral] "Text-to-image diffusion models can be easily backdoored through multimodal data poisoning"☆22Updated this week
- ☆20Updated 4 months ago
- ☆21Updated last year
- ☆48Updated last year
- Code of paper [CVPR'24: Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?]☆12Updated 7 months ago
- [NeurIPS 2023] Codes for DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification☆25Updated 8 months ago
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf☆17Updated 8 months ago
- A collection of resources on attacks and defenses targeting text-to-image diffusion models☆46Updated 2 weeks ago
- Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)☆33Updated last year
- [NeurIPS 2023] Differentially Private Image Classification by Learning Priors from Random Processes☆11Updated last year
- 🛡️[ICLR'2024] Toward effective protection against diffusion-based mimicry through score distillation, a.k.a SDS-Attack☆36Updated 7 months ago
- ☆19Updated 3 weeks ago
- Code Repo for the NeurIPS 2023 paper "VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models"☆19Updated 2 months ago
- [CVPR23W] "A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion" by Haomin Zhuang, Yihua Zhang and Sijia Liu☆24Updated 2 months ago
- ☆20Updated last year
- ☆54Updated 2 years ago
- [CVPR'24 Oral] Metacloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning☆19Updated this week
- The official implementation of ECCV'24 paper "To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Uns…☆58Updated 3 weeks ago
- [NeurIPS'2023] Official Code Repo:Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability☆88Updated last year
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images☆24Updated 10 months ago
- ☆25Updated 4 months ago
- ICCV 2021, We find most existing triggers of backdoor attacks in deep learning contain severe artifacts in the frequency domain. This Rep…☆41Updated 2 years ago
- Code for the paper "Autoregressive Perturbations for Data Poisoning" (NeurIPS 2022)☆18Updated 2 months ago
- An Embarrassingly Simple Backdoor Attack on Self-supervised Learning☆15Updated 10 months ago
- ☆21Updated 6 months ago
- ☆56Updated 4 months ago
- Code implementation for "CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion" (CVPR 2024)☆12Updated 8 months ago