awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
thu-ml avatar

thu-ml/Attack-Bard

0
View on GitHub↗
108 stars·7 forks·Python·6 views

Attack Bard

[2023/10/14] We have updated the results on GPT-4V. The attack success rate is 45%!.

Features

  • Multimodal Attacks - Tests robustness of multimodal models against adversarial images.

Star history

Star history chart for thu-ml/attack-bardStar history chart for thu-ml/attack-bard

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Frequently asked questions

What does thu-ml/attack-bard do?

[2023/10/14] We have updated the results on GPT-4V. The attack success rate is 45%!.

What are the main features of thu-ml/attack-bard?

The main features of thu-ml/attack-bard are: Multimodal Attacks.

Which projects share features with thu-ml/attack-bard?

Projects with overlapping indexed features include: adversarial-for-goodness/co-attack — This is the official PyTorch implement of the paper "Towards Adversarial Attack on Vision-Language Pre-training… cgcl-codes/advclip — The implementation of our ACM MM 2023 paper "AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal… 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.

Projects sharing features with Attack Bard

These projects share indexed features with Attack Bard. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • cgcl-codes/advclipCGCL-codes avatar

    CGCL-codes/AdvCLIP

    99View on GitHub↗

    The implementation of our ACM MM 2023 paper "AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning"

    Python
    View on GitHub↗99
  • ericyinyzy/vlattackericyinyzy avatar

    ericyinyzy/VLAttack

    69View on GitHub↗

    VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models

    Jupyter Notebook
    View on GitHub↗69
  • euanong/image-hijackseuanong avatar

    euanong/image-hijacks

    55View on GitHub↗

    This is the code for Image Hijacks: Adversarial Images can Control Generative Models at Runtime.

    Python
    View on GitHub↗55
  • adversarial-for-goodness/co-attackadversarial-for-goodness avatar

    adversarial-for-goodness/Co-Attack

    68View on GitHub↗

    This is the official PyTorch implement of the paper "Towards Adversarial Attack on Vision-Language Pre-training Models" at ACM Multimedia 2022.

    Python
    View on GitHub↗68
Compare all 12 related projects
→