Adaptive differential private in deep learning

Hao Fei; Gehao Lu; Yaling Luo

doi:10.1117/12.2679158

25 May 2023 Adaptive differential private in deep learning

Hao Fei, Gehao Lu, Yaling Luo

Proceedings Volume 12712, International Conference on Cloud Computing, Performance Computing, and Deep Learning (CCPCDL 2023); 127121L (2023) https://doi.org/10.1117/12.2679158
Event: International Conference on Cloud Computing, Performance Computing, and Deep Learning (CCPCDL 2023), 2023, Huzhou, China

Abstract

With the continuous development of artificial intelligence, it embodies important value in more and more scenarios, such as speech recognition, recommendation systems, computer vision, etc. The deep learning techniques behind them are built on a large amount of data to learn and extract features from different data. The deep learning techniques behind them are built on a large amount of data, learning from different data and extracting features. To protect data security, differential privacy is a good mechanism which is independent of the background knowledge possessed by the attacker and shows excellent results in privacy protection. In this paper, based on differential privacy and combined with knowledge in deep learning optimizer, We propose Adam-DP to improve the learning efficiency by adapting the learning rate and noise, and the adaptive noise also reduces the impact of noise on the model accuracy to some extent. The experiments show that the method has higher accuracy and learning rate compared with the DPSGD method.

Citation Download Citation

Hao Fei, Gehao Lu, and Yaling Luo "Adaptive differential private in deep learning", Proc. SPIE 12712, International Conference on Cloud Computing, Performance Computing, and Deep Learning (CCPCDL 2023), 127121L (25 May 2023); https://doi.org/10.1117/12.2679158

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
9 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Deep learning

Education and training

Data privacy

Detection and tracking algorithms

Mathematical optimization

Data modeling

Feature extraction

Show All Keywords

Keywords/Phrases

Search In:

Publication Years