Securing edge deep neural network against input evasion and IP theft
Deep learning is a key driver that puts artificial intelligence (AI) on the radar screen for technology investment. Deep Neural Network (DNN) automatically learns high-level features directly from raw data in a hierarchical manner, which eliminates manual extraction of effective features in traditio...
Main Author: | Wang, Si |
---|---|
Other Authors: | Chang Chip Hong |
Format: | Thesis-Doctor of Philosophy |
Language: | English |
Published: |
Nanyang Technological University
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/152267 |
Similar Items
-
Geometry estimation by deep neural network
by: Mei, Jianhan
Published: (2022) -
Predicting drug responses from drug chemical features by using deep neural networks
by: Krithika Ramamoorthy
Published: (2021) -
Image recognition based on deep learning of convolutional neural networks
by: Xie, Cong
Published: (2019) -
Image quality assessment based label smoothing in deep neural network learning
by: Chen, Zhou
Published: (2018) -
Evaluation of adversarial attacks against deep learning models
by: Chua, Jonathan Wen Rong
Published: (2023)