LiangSiyuan21 / BadCLIPLinks
☆24Updated 11 months ago
Alternatives and similar repositories for BadCLIP
Users that are interested in BadCLIP are comparing it to the libraries listed below
Sorting:
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf☆21Updated last year
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images☆37Updated last year
- ☆37Updated last year
- A package that achieves 95%+ transfer attack success rate against GPT-4☆23Updated 9 months ago
- [ICCV-2025] Universal Adversarial Attack, Multimodal Adversarial Attacks, VLP models, Contrastive Learning, Cross-modal Perturbation Gene…☆23Updated 3 weeks ago
- Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107☆17Updated 11 months ago
- ☆49Updated last year
- [ICML 2025] X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP☆24Updated last month
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆26Updated 9 months ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆51Updated 6 months ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆65Updated last year
- ☆31Updated 2 months ago
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2…☆56Updated 4 months ago
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models☆55Updated last year
- ☆46Updated 8 months ago
- ☆49Updated 11 months ago
- [CVPR 2024] "Data Poisoning based Backdoor Attacks to Contrastive Learning": official code implementation.☆16Updated 5 months ago
- A collection of resources on attacks and defenses targeting text-to-image diffusion models☆72Updated 4 months ago
- [CVPR 2023] The official implementation of our CVPR 2023 paper "Detecting Backdoors During the Inference Stage Based on Corruption Robust…☆23Updated 2 years ago
- Code for "Adversarial Illusions in Multi-Modal Embeddings"☆26Updated last year
- [CVPR 2024] Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers☆17Updated 9 months ago
- [MM'23 Oral] "Text-to-image diffusion models can be easily backdoored through multimodal data poisoning"☆29Updated 5 months ago
- ☆20Updated last year
- Code repository for CVPR2024 paper 《Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness》☆21Updated last year
- Code Repo for the NeurIPS 2023 paper "VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models"☆25Updated 3 months ago
- List of T2I safety papers, updated daily, welcome to discuss using Discussions☆62Updated 11 months ago
- [CVPR2025] Official Repository for IMMUNE: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment☆22Updated last month
- [CVPR 2023] Backdoor Defense via Adaptively Splitting Poisoned Dataset☆48Updated last year
- ☆102Updated last year
- CVPR 2025 - Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models☆41Updated last month