Skip to content
@HKU-TASR

HKU Trustworthy AI and Systems Research (TASR) Lab

Popular repositories Loading

  1. Imperio Imperio Public

    [IJCAI 2024] Imperio is an LLM-powered backdoor attack. It allows the adversary to issue language-guided instructions to control the victim model's prediction for arbitrary targets.

    Python 42 4

  2. Geminio Geminio Public

    Geminio is a VLM-powered gradient inversion attack in federated learning (FL). It allows the adversary (the FL server) to describe the data of value and reconstruct the victim client's private data…

    Python 5

  3. AnywhereDoor AnywhereDoor Public

    AnywhereDoor is a multi-target backdoor attack tailored for object detection. Once implanted, it enables adversaries to specify different attack types (object vanishing, fabrication, or misclassifi…

    Jupyter Notebook 2

  4. Sanitizer Sanitizer Public

    Sanitizer is a server-side method that ensures client-embedded backdoors can only be used for contribution demonstration in federated learning but not be triggered on natural queries in harmful ways.

    Python 2

Repositories

Showing 4 of 4 repositories
  • Sanitizer Public

    Sanitizer is a server-side method that ensures client-embedded backdoors can only be used for contribution demonstration in federated learning but not be triggered on natural queries in harmful ways.

    HKU-TASR/Sanitizer’s past year of commit activity
    Python 2 MIT 0 0 0 Updated Dec 8, 2024
  • Geminio Public

    Geminio is a VLM-powered gradient inversion attack in federated learning (FL). It allows the adversary (the FL server) to describe the data of value and reconstruct the victim client's private data matching the description.

    HKU-TASR/Geminio’s past year of commit activity
    Python 5 MIT 0 0 0 Updated Dec 6, 2024
  • AnywhereDoor Public

    AnywhereDoor is a multi-target backdoor attack tailored for object detection. Once implanted, it enables adversaries to specify different attack types (object vanishing, fabrication, or misclassification) and configurations (untargeted or targeted with specific classes) to dynamically control detection behavior.

    HKU-TASR/AnywhereDoor’s past year of commit activity
    Jupyter Notebook 2 MIT 0 0 0 Updated Dec 6, 2024
  • Imperio Public

    [IJCAI 2024] Imperio is an LLM-powered backdoor attack. It allows the adversary to issue language-guided instructions to control the victim model's prediction for arbitrary targets.

    HKU-TASR/Imperio’s past year of commit activity
    Python 42 MIT 4 1 0 Updated Apr 17, 2024

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…