3 papers
cs.CV2025
BadHMP: Backdoor Attack against Human Motion Prediction
Chaohui Xu, Si Wang, Chip-Hong Chang
Precise future human motion prediction over sub-second horizons from past observations is crucial for various safety-critical applications. To date, only a few studies have examine…
cs.CR2025
CHIP: Chameleon Hash-based Irreversible Passport for Robust Deep Model Ownership Verification and Active Usage Control
Chaohui Xu, Qi Cui, Chip-Hong Chang
The pervasion of large-scale Deep Neural Networks (DNNs) and their enormous training costs make their intellectual property (IP) protection of paramount importance. Recently introd…
cs.CR2025
IDEA: An Inverse Domain Expert Adaptation Based Active DNN IP Protection Method
Chaohui Xu, Qi Cui, Jinxin Dong +2
Illegitimate reproduction, distribution and derivation of Deep Neural Network (DNN) models can inflict economic loss, reputation damage and even privacy infringement. Passive DNN i…