A Survey of Security Protection Methods for Deep Learning Model
H Peng, S Bao, L Li - IEEE Transactions on Artificial Intelligence, 2023 - ieeexplore.ieee.org
In recent years, deep learning (DL) models have attracted widespread concern. Due to its
own characteristics, DL has been successfully applied in the fields of object detection …
own characteristics, DL has been successfully applied in the fields of object detection …
可逆神经网络的隐私泄露风险评估
何毅凡， 张杰， 张卫明， 俞能海 - 网络与信息安全学报, 2023 - infocomm-journal.com
近年来, 深度学习已经成为多方领域的核心技术, 而深度学习模型的训练过程中往往需要大量的
数据, 这些数据中可能含有隐私信息, 包括个人身份信息(如电话号码, 身份证号等) …
数据, 这些数据中可能含有隐私信息, 包括个人身份信息(如电话号码, 身份证号等) …
[图书][B] Secure Reconfigurable Computing Paradigms for the Next Generation of Artificial Intelligence and Machine Learning Applications
B Olney - 2023 - search.proquest.com
The fields of artificial intelligence (AI) and machine learning (ML) have been popular tools
for data analysis at the edge, particularly through complex deep and convolutional neural …
for data analysis at the edge, particularly through complex deep and convolutional neural …
An Enhanced Adversarial Attacks Method on Power System Based on Model Extraction Algorithm
Y Ma, Q Wang, Z Liu, C Hong - 2022 IEEE 6th Conference on …, 2022 - ieeexplore.ieee.org
Artificial intelligence algorithms fit connections between features and problems from a data-
driven perspective. Artificial intelligence algorithms perform iterative training of data through …
driven perspective. Artificial intelligence algorithms perform iterative training of data through …