DuetFace: Collaborative Privacy-Preserving Face Recognition via Channel Splitting in the Frequency Domain

TL;DR

DuetFace introduces a privacy-preserving face recognition approach that splits frequency channels between client and server, maintaining high accuracy while protecting visual privacy through collaborative inference and attention transfer.

Contribution

The paper proposes a novel frequency channel splitting method for privacy-preserving face recognition, utilizing collaborative inference and attention transfer to balance privacy and performance.

Findings

Achieves comparable accuracy to unprotected models.

Effectively prevents visual reconstruction and identification.

Outperforms existing privacy-preserving methods.

Abstract

With the wide application of face recognition systems, there is rising concern that original face images could be exposed to malicious intents and consequently cause personal privacy breaches. This paper presents DuetFace, a novel privacy-preserving face recognition method that employs collaborative inference in the frequency domain. Starting from a counterintuitive discovery that face recognition can achieve surprisingly good performance with only visually indistinguishable high-frequency channels, this method designs a credible split of frequency channels by their cruciality for visualization and operates the server-side model on non-crucial channels. However, the model degrades in its attention to facial features due to the missing visual information. To compensate, the method introduces a plug-in interactive block to allow attention transfer from the client-side by producing a feature mask. The mask is further refined by deriving and overlaying a facial region of interest (ROI). Extensive experiments on multiple datasets validate the effectiveness of the proposed method in protecting face images from undesired visual inspection, reconstruction, and identification while maintaining high task availability and performance. Results show that the proposed method achieves a comparable recognition accuracy and computation cost to the unprotected ArcFace and outperforms the state-of-the-art privacy-preserving methods. The source code is available at https://github.com/Tencent/TFace/tree/master/recognition/tasks/duetface.