Disguise without Disruption: Utility-Preserving Face De-Identification

• URL: http://arxiv.org/abs/2303.13269v2
• Date: Mon, 18 Dec 2023 15:33:42 GMT
• Title: Disguise without Disruption: Utility-Preserving Face De-Identification
• Authors: Zikui Cai, Zhongpai Gao, Benjamin Planche, Meng Zheng, Terrence Chen, M. Salman Asif, Ziyan Wu
• Abstract summary: We introduce Disguise, a novel algorithm that seamlessly de-identifies facial images while ensuring the usability of the modified data. Our method involves extracting and substituting depicted identities with synthetic ones, generated using variational mechanisms to maximize obfuscation and non-invertibility. We extensively evaluate our method using multiple datasets, demonstrating a higher de-identification rate and superior consistency compared to prior approaches in various downstream tasks.
• Score: 40.484745636190034
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the rise of cameras and smart sensors, humanity generates an exponential amount of data. This valuable information, including underrepresented cases like AI in medical settings, can fuel new deep-learning tools. However, data scientists must prioritize ensuring privacy for individuals in these untapped datasets, especially for images or videos with faces, which are prime targets for identification methods. Proposed solutions to de-identify such images often compromise non-identifying facial attributes relevant to downstream tasks. In this paper, we introduce Disguise, a novel algorithm that seamlessly de-identifies facial images while ensuring the usability of the modified data. Unlike previous approaches, our solution is firmly grounded in the domains of differential privacy and ensemble-learning research. Our method involves extracting and substituting depicted identities with synthetic ones, generated using variational mechanisms to maximize obfuscation and non-invertibility. Additionally, we leverage supervision from a mixture-of-experts to disentangle and preserve other utility attributes. We extensively evaluate our method using multiple datasets, demonstrating a higher de-identification rate and superior consistency compared to prior approaches in various downstream tasks.

Related papers

• Semantic Contextualization of Face Forgery: A New Definition, Dataset, and Detection Method [77.65459419417533]
  We put face forgery in a semantic context and define that computational methods that alter semantic face attributes are sources of face forgery. We construct a large face forgery image dataset, where each image is associated with a set of labels organized in a hierarchical graph. We propose a semantics-oriented face forgery detection method that captures label relations and prioritizes the primary task.
  arXiv  Detail & Related papers  (2024-05-14T10:24:19Z)
• Privacy-preserving Optics for Enhancing Protection in Face De-identification [60.110274007388135]
  We propose a hardware-level face de-identification method to solve this vulnerability. We also propose an anonymization framework that generates a new face using the privacy-preserving image, face heatmap, and a reference face image from a public dataset as input.
  arXiv  Detail & Related papers  (2024-03-31T19:28:04Z)
• Latent Diffusion Models for Attribute-Preserving Image Anonymization [4.080920304681247]
  This paper presents the first approach to image anonymization based on Latent Diffusion Models (LDMs) We propose two LDMs for this purpose: CAFLaGE-Base exploits a combination of pre-trained ControlNets, and a new controlling mechanism designed to increase the distance between the real and anonymized images.
  arXiv  Detail & Related papers  (2024-03-21T19:09:21Z)
• Embedding Non-Distortive Cancelable Face Template Generation [22.80706131626207]
  We introduce an innovative image distortion technique that makes facial images unrecognizable to the eye but still identifiable by any custom embedding neural network model. We test the reliability of biometric recognition networks by determining the maximum image distortion that does not change the predicted identity.
  arXiv  Detail & Related papers  (2024-02-04T15:39:18Z)
• Unrecognizable Yet Identifiable: Image Distortion with Preserved Embeddings [22.338328674283062]
  We introduce an innovative image transformation technique that renders facial images unrecognizable to the eye while maintaining their identifiability by neural network models. The proposed methodology can be used in various artificial intelligence applications to distort the visual data and keep the derived features close. We show that it is possible to build the distortion that changes the image content by more than 70% while maintaining the same recognition accuracy.
  arXiv  Detail & Related papers  (2024-01-26T18:20:53Z)
• 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)
• Attribute-preserving Face Dataset Anonymization via Latent Code Optimization [64.4569739006591]
  We present a task-agnostic anonymization procedure that directly optimize the images' latent representation in the latent space of a pre-trained GAN. We demonstrate through a series of experiments that our method is capable of anonymizing the identity of the images whilst -- crucially -- better-preserving the facial attributes.
  arXiv  Detail & Related papers  (2023-03-20T17:34:05Z)
• Unsupervised Face Recognition using Unlabeled Synthetic Data [16.494722503803196]
  We propose an unsupervised face recognition model based on unlabeled synthetic data (U SynthFace) Our proposed U SynthFace learns to maximize the similarity between two augmented images of the same synthetic instance. We prove the effectiveness of our U SynthFace in achieving relatively high recognition accuracies using unlabeled synthetic data.
  arXiv  Detail & Related papers  (2022-11-14T14:05:19Z)
• 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)

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.