ai-data-model-safety / ai-data-model-safety.github.io
☆26Updated last month
Alternatives and similar repositories for ai-data-model-safety.github.io:
Users that are interested in ai-data-model-safety.github.io are comparing it to the libraries listed below
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2…☆41Updated 2 months ago
- Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Models☆20Updated last month
- ☆40Updated 5 months ago
- ☆64Updated 6 months ago
- ☆12Updated last year
- official PyTorch implement of Towards Adversarial Attack on Vision-Language Pre-training Models☆53Updated last year
- ☆33Updated last month
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆37Updated 7 months ago
- [CVPR 2023] The official implementation of our CVPR 2023 paper "Detecting Backdoors During the Inference Stage Based on Corruption Robust…☆21Updated last year
- Official code for our NDSS paper "Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarkin…☆25Updated 2 months ago
- A curated list of papers for the transferability of adversarial examples☆58Updated 6 months ago
- Divide-and-Conquer Attack: Harnessing the Power of LLM to Bypass the Censorship of Text-to-Image Generation Mode☆18Updated 4 months ago
- ☆23Updated last year
- A package that achieves 95%+ transfer attack success rate against GPT-4☆17Updated 3 months ago
- Composite Backdoor Attacks Against Large Language Models☆11Updated 9 months ago
- [ECCV2024] Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajector…☆20Updated 2 months ago
- ☆29Updated 7 months ago
- Source code and scripts for the paper "Is Difficulty Calibration All We Need? Towards More Practical Membership Inference Attacks"☆15Updated last month
- Code for paper: "PromptCARE: Prompt Copyright Protection by Watermark Injection and Verification", IEEE S&P 2024.☆30Updated 5 months ago
- ☆20Updated 4 months ago
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf☆18Updated 10 months ago
- [CVPR23W] "A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion" by Haomin Zhuang, Yihua Zhang and Sijia Liu☆25Updated 5 months ago
- ☆15Updated 2 weeks ago
- Universal Adversarial Attack, Multimodal Adversarial Attacks, VLP models, Contrastive Learning, Cross-modal Perturbation Generator, Gener…☆13Updated 3 months ago
- This Github repository summarizes a list of research papers on AI security from the four top academic conferences.☆105Updated last year
- Invisible Backdoor Attack with Sample-Specific Triggers☆93Updated 2 years ago
- [CVPR 2023] Backdoor Defense via Adaptively Splitting Poisoned Dataset☆46Updated 9 months ago
- ☆18Updated 2 years ago
- 复现了下Neural Cleanse这篇论文，真的是简单而有效，发在了okaland☆30Updated 3 years ago
- Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models. [ICCV 2023 Oral]☆51Updated last year