Secure Visual Data Processing via Federated Learning

TL;DR

This paper proposes a novel privacy-preserving framework for visual data processing that combines object detection, federated learning, and anonymization to enhance privacy protections in sensitive applications.

Contribution

It introduces an integrated approach that addresses the limitations of existing methods by combining three privacy-preserving techniques for visual data.

Findings

Achieves substantial privacy protection compared to centralized models.

Maintains acceptable accuracy with a slight trade-off.

Effective in privacy-sensitive visual data applications.

Abstract

As the demand for privacy in visual data management grows, safeguarding sensitive information has become a critical challenge. This paper addresses the need for privacy-preserving solutions in large-scale visual data processing by leveraging federated learning. Although there have been developments in this field, previous research has mainly focused on integrating object detection with either anonymization or federated learning. However, these pairs often fail to address complex privacy concerns. On the one hand, object detection with anonymization alone can be vulnerable to reverse techniques. On the other hand, federated learning may not provide sufficient privacy guarantees. Therefore, we propose a new approach that combines object detection, federated learning and anonymization. Combining these three components aims to offer a robust privacy protection strategy by addressing different vulnerabilities in visual data. Our solution is evaluated against traditional centralized models, showing that while there is a slight trade-off in accuracy, the privacy benefits are substantial, making it well-suited for privacy sensitive applications.