Privacy-Preserving Face Recognition in Hybrid Frequency-Color Domain

• URL: http://arxiv.org/abs/2401.13386v1
• Date: Wed, 24 Jan 2024 11:27:32 GMT
• Title: Privacy-Preserving Face Recognition in Hybrid Frequency-Color Domain
• Authors: Dong Han, Yong Li, Joachim Denzler
• Abstract summary: Face image is a sensitive biometric attribute tied to the identity information of each user. This paper proposes a hybrid frequency-color fusion approach to reduce the input dimensionality of face recognition. It has around 2.6% to 4.2% higher accuracy than the state-of-the-art in the 1:N verification scenario.
• Score: 16.05230409730324
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Face recognition technology has been deployed in various real-life applications. The most sophisticated deep learning-based face recognition systems rely on training millions of face images through complex deep neural networks to achieve high accuracy. It is quite common for clients to upload face images to the service provider in order to access the model inference. However, the face image is a type of sensitive biometric attribute tied to the identity information of each user. Directly exposing the raw face image to the service provider poses a threat to the user's privacy. Current privacy-preserving approaches to face recognition focus on either concealing visual information on model input or protecting model output face embedding. The noticeable drop in recognition accuracy is a pitfall for most methods. This paper proposes a hybrid frequency-color fusion approach to reduce the input dimensionality of face recognition in the frequency domain. Moreover, sparse color information is also introduced to alleviate significant accuracy degradation after adding differential privacy noise. Besides, an identity-specific embedding mapping scheme is applied to protect original face embedding by enlarging the distance among identities. Lastly, secure multiparty computation is implemented for safely computing the embedding distance during model inference. The proposed method performs well on multiple widely used verification datasets. Moreover, it has around 2.6% to 4.2% higher accuracy than the state-of-the-art in the 1:N verification scenario.

Related papers

• Privacy-Preserving Face Recognition Using Trainable Feature Subtraction [40.47645421424354]
  Face recognition has led to increasing privacy concerns. This paper explores face image protection against viewing and recovery attacks. We distill our methodologies into a novel privacy-preserving face recognition method, MinusFace.
  arXiv  Detail & Related papers  (2024-03-19T05:27:52Z)
• Diff-Privacy: Diffusion-based Face Privacy Protection [58.1021066224765]
  In this paper, we propose a novel face privacy protection method based on diffusion models, dubbed Diff-Privacy. Specifically, we train our proposed multi-scale image inversion module (MSI) to obtain a set of SDM format conditional embeddings of the original image. Based on the conditional embeddings, we design corresponding embedding scheduling strategies and construct different energy functions during the denoising process to achieve anonymization and visual identity information hiding.
  arXiv  Detail & Related papers  (2023-09-11T09:26:07Z)
• Privacy-Preserving Face Recognition Using Random Frequency Components [46.95003101593304]
  Face recognition has sparked increasing privacy concerns. We propose to conceal visual information by pruning human-perceivable low-frequency components. We distill our findings into a novel privacy-preserving face recognition method, PartialFace.
  arXiv  Detail & Related papers  (2023-08-21T04:31:02Z)
• Face Encryption via Frequency-Restricted Identity-Agnostic Attacks [25.198662208981467]
  Malicious collectors use deep face recognition systems to easily steal biometric information. We propose a frequency-restricted identity-agnostic (FRIA) framework to encrypt face images from unauthorized face recognition.
  arXiv  Detail & Related papers  (2023-08-11T07:38:46Z)
• DuetFace: Collaborative Privacy-Preserving Face Recognition via Channel Splitting in the Frequency Domain [23.4606547767188]
  DuetFace is a privacy-preserving face recognition method that employs collaborative inference in the frequency domain. The proposed method achieves a comparable recognition accuracy and cost to the unprotected ArcFace and outperforms the state-of-the-art privacy-preserving methods.
  arXiv  Detail & Related papers  (2022-07-15T08:35:44Z)
• Privacy-Preserving Face Recognition with Learnable Privacy Budgets in Frequency Domain [77.8858706250075]
  This paper proposes a privacy-preserving face recognition method using differential privacy in the frequency domain. Our method performs very well with several classical face recognition test sets.
  arXiv  Detail & Related papers  (2022-07-15T07:15:36Z)
• OPOM: Customized Invisible Cloak towards Face Privacy Protection [58.07786010689529]
  We investigate the face privacy protection from a technology standpoint based on a new type of customized cloak. We propose a new method, named one person one mask (OPOM), to generate person-specific (class-wise) universal masks. The effectiveness of the proposed method is evaluated on both common and celebrity datasets.
  arXiv  Detail & Related papers  (2022-05-24T11:29:37Z)
• Towards Face Encryption by Generating Adversarial Identity Masks [53.82211571716117]
  We propose a targeted identity-protection iterative method (TIP-IM) to generate adversarial identity masks. TIP-IM provides 95%+ protection success rate against various state-of-the-art face recognition models.
  arXiv  Detail & Related papers  (2020-03-15T12:45:10Z)
• Investigating the Impact of Inclusion in Face Recognition Training Data on Individual Face Identification [93.5538147928669]
  We audit ArcFace, a state-of-the-art, open source face recognition system, in a large-scale face identification experiment with more than one million distractor images. We find a Rank-1 face identification accuracy of 79.71% for individuals present in the model's training data and an accuracy of 75.73% for those not present.
  arXiv  Detail & Related papers  (2020-01-09T15:50:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.