HKU Trustworthy AI and Systems Research (TASR) Lab
- 16 followers
- Hong Kong
- https://khchow.com
- kachow@cs.hku.hk
Popular repositories Loading
-
AnywhereDoor
AnywhereDoor PublicAnywhereDoor 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…
Repositories
- 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 - Confundo Public
[USENIX Security 2026] Confundo: Learning to Generate Robust Poison for Practical RAG Systems
HKU-TASR/Confundo’s past year of commit activity - 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 - 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 - 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 - 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 - 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 - 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 - Chameleon Public Forked from git-disl/Chameleon
[ECCV 2024] Chameleon learns to generate a user-centric personalized privacy protection mask, coined as P3-Mask, to protect facial images against unauthorized face recognition.
HKU-TASR/Chameleon’s past year of commit activity
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…