Financial Vision Based Differential Privacy Applications

TL;DR

This paper evaluates the application of two deep learning privacy frameworks, DP-SGD and PATE, to financial trading data, demonstrating that DP-SGD offers better privacy-accuracy tradeoffs and aligns with real-world privacy standards.

Contribution

It is the first study to apply Google’s deep learning privacy frameworks to financial trading data, comparing their effectiveness and privacy guarantees in this domain.

Findings

DP-SGD outperforms PATE in privacy-accuracy tradeoff.

DP-SGD provides strong privacy guarantees with minimal accuracy loss.

Results align with privacy standards of Google and Apple.

Abstract

The importance of deep learning data privacy has gained significant attention in recent years. It is probably to suffer data breaches when applying deep learning to cryptocurrency that lacks supervision of financial regulatory agencies. However, there is little relative research in the financial area to our best knowledge. We apply two representative deep learning privacy-privacy frameworks proposed by Google to financial trading data. We designed the experiments with several different parameters suggested from the original studies. In addition, we refer the degree of privacy to Google and Apple companies to estimate the results more reasonably. The results show that DP-SGD performs better than the PATE framework in financial trading data. The tradeoff between privacy and accuracy is low in DP-SGD. The degree of privacy also is in line with the actual case. Therefore, we can obtain a strong privacy guarantee with precision to avoid potential financial loss.