AdaBias: An Optimization Method With Bias Correction for Differential Privacy Protection
Ieee Access
; 10:107010-107021, 2022.
Article
in English
| Web of Science | ID: covidwho-2083045
ABSTRACT
A continuous increase in privacy attacks has caused the research and application of differential privacy (DP) to gradually increase. We can improve the efficiency of the DP model by Optimizing its parameters significantly. Inspired by the performance of various optimization methods for differential privacy, this paper proposes an improved RDP-AdaBound optimization method with bias correction, which is called "AdaBias", to increase the performance of Renyi differential privacy (RDP). The bias correction is used to realize the learning rate and speed up the convergence by upper and lower bound functions. We evaluate our method on the three datasets by training two different privacy model. We further compare three traditional optimization algorithms, namely, RDP-SGD, RDP-Adagrad, and RDP-Adam. And we use AdaBias to verify the performance of privacy protection on the COVID-19 dataset. Experimental results show that the new variant better implements learning rate adjustment to accommodate updates of noisy gradients. As a result, it can achieve higher accuracy and lower losses with a lower privacy budget, thereby better protecting data privacy.
Full text:
Available
Collection:
Databases of international organizations
Database:
Web of Science
Language:
English
Journal:
Ieee Access
Year:
2022
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS