How this analysis was created: This summary and feature list were written by an AI model that read the project's README and public documentation pages. Each feature links to the documentation it came from; stars, license and language come straight from the GitHub API. The model does not read the source code, and the analysis is refreshed when the project is re-analysed. Learn more on our About page.
[NeurIPS-2023] Annual Conference on Neural Information Processing Systems
The main features of yunqing-me/attackvlm are: Multimodal Attacks, Model Utilities.
Open-source alternatives to yunqing-me/attackvlm include: ailab-cvc/seed — Official implementation of SEED-LLaMA (ICLR 2024). cgcl-codes/advclip — The implementation of our ACM MM 2023 paper "AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal… dvlab-research/prompt-highlighter — [CVPR 2024] Prompt Highlighter: Interactive Control for Multi-Modal LLMs. ericyinyzy/vlattack — VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models. euanong/image-hijacks — This is the code for Image Hijacks: Adversarial Images can Control Generative Models at Runtime. adversarial-for-goodness/co-attack — This is the official PyTorch implement of the paper "Towards Adversarial Attack on Vision-Language Pre-training…
The implementation of our ACM MM 2023 paper "AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning"
CVPR 2024 Prompt Highlighter: Interactive Control for Multi-Modal LLMs
This is the official PyTorch implement of the paper "Towards Adversarial Attack on Vision-Language Pre-training Models" at ACM Multimedia 2022.
