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 44 4

  2. Geminio Geminio Public

    [ICCV 2025] 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 …

    Python 10 4

  3. Protego Protego Public

    [CVPR 2026] Protego is a user-centric privacy protection method that safeguards facial images from retrieval-based privacy intrusions.

    Jupyter Notebook 10 2

  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 9 3

  5. Confundo Confundo Public

    [SEC 2026] Confundo: Learning to Generate Robust Poison for Practical RAG Systems

    Python 9

  6. 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 8

Repositories

Showing 10 of 12 repositories
  • FRBench Public

    An easy-to-use, end-to-end differentiable face-recognition module that ships 45+ pretrained weights, covering 25 backbones, 9 loss functions, and 3 training datasets spanning generations since 2015.

    HKU-TASR/FRBench's past year of commit activity
    Jupyter Notebook 3 MIT 0 0 0 Updated Sep 12, 2026
  • BVBench Public

    A Benchmark for Studying VFL Backdoor Vulnerabilities

    HKU-TASR/BVBench's past year of commit activity
    Python 0 MIT 0 0 0 Updated Aug 13, 2026
  • TRivia Public Forked from opendatalab/TRivia

    [CVPR 2026] TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognition

    HKU-TASR/TRivia's past year of commit activity
    Python 1 Apache-2.0 5 0 0 Updated Jul 14, 2026
  • Protego Public

    [CVPR 2026] Protego is a user-centric privacy protection method that safeguards facial images from retrieval-based privacy intrusions.

    HKU-TASR/Protego's past year of commit activity
    Jupyter Notebook 10 2 1 0 Updated Jul 13, 2026
  • Proteus Public

    [ECCV 2026] Proteus: Model Leakage-Induced Adversarial Attack in Federated Learning

    HKU-TASR/Proteus's past year of commit activity
    Python 0 MIT 0 0 0 Updated Jun 29, 2026
  • Confundo Public

    [SEC 2026] Confundo: Learning to Generate Robust Poison for Practical RAG Systems

    HKU-TASR/Confundo's past year of commit activity
    Python 9 MIT 0 0 0 Updated Jun 6, 2026
  • GDBR Public

    [EuroS&P 2026] GDBR: Label Recovery Attack Against Partial Gradient Encryption in Federated Learning

    HKU-TASR/GDBR's past year of commit activity
    0 MIT 0 0 0 Updated Mar 8, 2026
  • Geminio Public

    [ICCV 2025] 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 10 MIT 4 0 0 Updated Aug 7, 2025
  • 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 9 MIT 3 1 1 Updated Jul 8, 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.

    HKU-TASR/Sanitizer's past year of commit activity
    Python 8 MIT 0 1 0 Updated Jun 25, 2025
View all repositories

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…