Activity Recognition on Avatar-Anonymized Datasets with Masked Differential Privacy

TL;DR

This paper introduces an anonymization pipeline using synthetic avatars and a masked differential privacy technique to enhance privacy in action recognition datasets while maintaining high utility.

Contribution

It presents a novel avatar-based anonymization method combined with MaskDP, enabling targeted privacy protection with less utility loss.

Findings

Improved utility-privacy trade-offs over standard DP methods

Effective anonymization with synthetic avatars in video datasets

Strong privacy protection in action recognition tasks

Abstract

Privacy-preserving computer vision is an important emerging problem in machine learning and artificial intelligence. Prevalent methods tackling this problem use differential privacy (DP) or obfuscation techniques to protect the privacy of individuals. In both cases, the utility of the trained model is sacrificed heavily in this process. In this work, we present an anonymization pipeline that replaces sensitive human subjects in video datasets with synthetic avatars within context, employing a combined rendering and stable diffusion-based strategy. Additionally we propose masked differential privacy ({MaskDP}) to protect non-anonymized but privacy sensitive background information. MaskDP allows for controlling sensitive regions where differential privacy is applied, in contrast to applying DP on the entire input. This combined methodology provides strong privacy protection while minimizing the usual performance penalty of privacy preserving methods. Experiments on multiple challenging action recognition datasets demonstrate that our proposed techniques result in better utility-privacy trade-offs compared to standard differentially private training in the especially demanding $\epsilon<1$ regime.