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 41 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. Sanitizer Sanitizer Public

    [EuroS&P 2025] 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…

    Python 3

  4. 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 1

Repositories

Showing 4 of 4 repositories
  • 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.

    Jupyter Notebook 2 MIT 1 0 1 Updated Mar 11, 2025
  • 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.

    Python 5 MIT 0 0 0 Updated Mar 6, 2025
  • Sanitizer Public

    [EuroS&P 2025] 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 3 MIT 0 0 0 Updated Mar 2, 2025
  • 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 41 MIT 4 1 0 Updated Feb 18, 2025

People

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

Top languages

Loading…