VITA-Group / Shake-to-Leak
☆14Updated 2 months ago
Related projects: ⓘ
- The official implementation of ECCV'24 paper "To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Uns…☆43Updated last month
- Official implementation of "Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models"☆17Updated last month
- [CVPR'24 Oral] Metacloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning☆18Updated 2 months ago
- [CVPR23W] "A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion" by Haomin Zhuang, Yihua Zhang and Sijia Liu☆21Updated 3 weeks ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆14Updated 3 months ago
- [ECCV-2024] Transferable Targeted Adversarial Attack, CLIP models, Generative adversarial network, Multi-target attacks☆18Updated last month
- ☆52Updated last year
- One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models☆31Updated 4 months ago
- Code for the paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆21Updated 5 months ago
- ☆12Updated 2 years ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images☆17Updated 7 months ago
- [CVPR 2023] Backdoor Defense via Adaptively Splitting Poisoned Dataset☆40Updated 5 months ago
- ☆13Updated 3 months ago
- Official repo to reproduce the paper "How to Backdoor Diffusion Models?" published at CVPR 2023☆77Updated last week
- ☆35Updated last year
- 🛡️[ICLR'2024] Toward effective protection against diffusion-based mimicry through score distillation, a.k.a SDS-Attack☆32Updated 5 months ago
- ☆22Updated last month
- Code Repo for the NeurIPS 2023 paper "VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models"☆15Updated last week
- ☆22Updated 2 months ago
- Code for the paper "Autoregressive Perturbations for Data Poisoning" (NeurIPS 2022)☆18Updated last week
- ☆18Updated this week
- [MM'23 Oral] "Text-to-image diffusion models can be easily backdoored through multimodal data poisoning"☆19Updated last week
- [CVPR 2024] This repository includes the official implementation our paper "Revisiting Adversarial Training at Scale"☆16Updated 4 months ago
- [NeurIPS 2023] Codes for DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification☆18Updated 6 months ago
- Official repo for An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization☆11Updated 6 months ago
- official implementation of Towards Robust Model Watermark via Reducing Parametric Vulnerability☆12Updated 3 months ago
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models☆39Updated 5 months ago
- Query-Efficient Data-Free Learning from Black-Box Models☆19Updated last year
- A list of research towards security&privacy in AI-Generated Content☆13Updated 4 months ago
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf☆14Updated 5 months ago