OPOM: Customized Invisible Cloak towards Face Privacy Protection

TL;DR

This paper introduces OPOM, a person-specific mask generation technique that effectively protects individual face privacy against face recognition systems by creating universal masks tailored to each user.

Contribution

The paper proposes a novel one person one mask (OPOM) method for generating customized universal masks to prevent face recognition, utilizing feature subspace modeling techniques.

Findings

OPOM effectively prevents face recognition across various models.

Person-specific masks outperform generic anonymization methods.

The approach is practical for video privacy protection.

Abstract

While convenient in daily life, face recognition technologies also raise privacy concerns for regular users on the social media since they could be used to analyze face images and videos, efficiently and surreptitiously without any security restrictions. In this paper, we investigate the face privacy protection from a technology standpoint based on a new type of customized cloak, which can be applied to all the images of a regular user, to prevent malicious face recognition systems from uncovering their identity. Specifically, we propose a new method, named one person one mask (OPOM), to generate person-specific (class-wise) universal masks by optimizing each training sample in the direction away from the feature subspace of the source identity. To make full use of the limited training images, we investigate several modeling methods, including affine hulls, class centers, and convex hulls, to obtain a better description of the feature subspace of source identities. The effectiveness of the proposed method is evaluated on both common and celebrity datasets against black-box face recognition models with different loss functions and network architectures. In addition, we discuss the advantages and potential problems of the proposed method. In particular, we conduct an application study on the privacy protection of a video dataset, Sherlock, to demonstrate the potential practical usage of the proposed method. Datasets and code are available at https://github.com/zhongyy/OPOM.