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.
The implementation of our ACM MM 2023 paper "AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning"
The main features of cgcl-codes/advclip are: Multimodal Attacks.
Open-source alternatives to cgcl-codes/advclip include: adversarial-for-goodness/co-attack — This is the official PyTorch implement of the paper "Towards Adversarial Attack on Vision-Language Pre-training… 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. haochen-luo/cropa — This repository contains the code and data for the paper "An Image Is Worth 1000 Lies: Transferability of Adversarial… kaiyuancui/ultrabreak — ICLR 2026. kim-minseon/apgp — Official PyTorch implementation of "Automatic Jailbreaking of the Text-to-Image Generative AI Systems".
VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models
This is the code for Image Hijacks: Adversarial Images can Control Generative Models at Runtime.
This repository contains the code and data for the paper "An Image Is Worth 1000 Lies: Transferability of Adversarial Images across Prompts on Vision-Language Models" accepted by ICLR 2024. Overview of CroPA The environment.yml file contains the necessary packages to run the code. You can create…
This is the official PyTorch implement of the paper "Towards Adversarial Attack on Vision-Language Pre-training Models" at ACM Multimedia 2022.