Jia Duan — accepted AI-conference papers

2021

Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domain

Jinyu Tian, Jiantao Zhou, Yuanman Li, Jia Duan

AAAI 2021technical

Deep neural networks (DNNs) have been shown to be vulnerable against adversarial examples (AEs), which are maliciously designed to cause dramatic model output errors. In this work, we reveal that normal examples (NEs) are insensitive to the fluctuations occurring at the highly-curved region of the d…

Cited by 67 Source ↗PDF ↗Scholar ↗

2021

Probabilistic Selective Encryption of Convolutional Neural Networks for Hierarchical Services

Jinyu Tian, Jiantao Zhou, Jia Duan

CVPR 2021poster

Model protection is vital when deploying Convolutional Neural Networks (CNNs) for commercial services, due to the massive costs of training them. In this work, we propose a selective encryption (SE) algorithm to protect CNN models from unauthorized access, with a unique feature of providing hierarch…

Cited by 16 PDF ↗Scholar ↗