Safe Fakes: Evaluating Face Anonymizers for Face Detectors

• URL: http://arxiv.org/abs/2104.11721v1
• Date: Fri, 23 Apr 2021 17:16:23 GMT
• Title: Safe Fakes: Evaluating Face Anonymizers for Face Detectors
• Authors: Sander R. Klomp (1 and 2), Matthew van Rijn (3), Rob G.J. Wijnhoven (2), Cees G.M. Snoek (3), Peter H.N. de With (1) ((1) Eindhoven University of Technology, (2) ViNotion B.V., (3) University of Amsterdam)
• Abstract summary: This paper presents the first empirical study on the effect of image anonymization on supervised training of face detectors. We compare conventional face anonymizers with three state-of-the-art Generative Adrial Network-based (GAN) methods. Although all tested anonymization methods lower the performance of trained face detectors, faces anonymized using GANs cause far smaller performance degradation than conventional methods.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Since the introduction of the GDPR and CCPA legislation, both public and private facial image datasets are increasingly scrutinized. Several datasets have been taken offline completely and some have been anonymized. However, it is unclear how anonymization impacts face detection performance. To our knowledge, this paper presents the first empirical study on the effect of image anonymization on supervised training of face detectors. We compare conventional face anonymizers with three state-of-the-art Generative Adversarial Network-based (GAN) methods, by training an off-the-shelf face detector on anonymized data. Our experiments investigate the suitability of anonymization methods for maintaining face detector performance, the effect of detectors overtraining on anonymization artefacts, dataset size for training an anonymizer, and the effect of training time of anonymization GANs. A final experiment investigates the correlation between common GAN evaluation metrics and the performance of a trained face detector. Although all tested anonymization methods lower the performance of trained face detectors, faces anonymized using GANs cause far smaller performance degradation than conventional methods. As the most important finding, the best-performing GAN, DeepPrivacy, removes identifiable faces for a face detector trained on anonymized data, resulting in a modest decrease from 91.0 to 88.3 mAP. In the last few years, there have been rapid improvements in realism of GAN-generated faces. We expect that further progression in GAN research will allow the use of Deep Fake technology for privacy-preserving Safe Fakes, without any performance degradation for training face detectors.

Related papers

• G2Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priors [71.69161292330504]
  Reversible face anonymization seeks to replace sensitive identity information in facial images with synthesized alternatives. This paper introduces Gtextsuperscript2Face, which leverages both generative and geometric priors to enhance identity manipulation. Our method outperforms existing state-of-the-art techniques in face anonymization and recovery, while preserving high data utility.
  arXiv  Detail & Related papers  (2024-08-18T12:36:47Z)
• Exploring Decision-based Black-box Attacks on Face Forgery Detection [53.181920529225906]
  Face forgery generation technologies generate vivid faces, which have raised public concerns about security and privacy. Although face forgery detection has successfully distinguished fake faces, recent studies have demonstrated that face forgery detectors are very vulnerable to adversarial examples.
  arXiv  Detail & Related papers  (2023-10-18T14:49:54Z)
• GANonymization: A GAN-based Face Anonymization Framework for Preserving Emotional Expressions [43.017036538109274]
  GANonymization is a novel face anonymization framework with facial expression-preserving abilities. Our approach is based on a high-level representation of a face, which is synthesized into an anonymized version based on a generative adversarial network (GAN)
  arXiv  Detail & Related papers  (2023-05-03T14:22:48Z)
• LDFA: Latent Diffusion Face Anonymization for Self-driving Applications [3.501026362812183]
  We introduce a novel deep learning-based pipeline for face anonymization in the context of ITS. We propose a two-stage method, which contains a face detection model followed by a latent diffusion model to generate realistic face in-paintings. Our experiment reveal that our pipeline is better suited to anonymize data for segmentation than naive methods and performes comparably with recent GAN-based methods.
  arXiv  Detail & Related papers  (2023-02-17T15:14:00Z)
• FaceMAE: Privacy-Preserving Face Recognition via Masked Autoencoders [81.21440457805932]
  We propose a novel framework FaceMAE, where the face privacy and recognition performance are considered simultaneously. randomly masked face images are used to train the reconstruction module in FaceMAE. We also perform sufficient privacy-preserving face recognition on several public face datasets.
  arXiv  Detail & Related papers  (2022-05-23T07:19:42Z)
• On the (Limited) Generalization of MasterFace Attacks and Its Relation to the Capacity of Face Representations [11.924504853735645]
  We study the generalizability of MasterFace attacks in empirical and theoretical investigations. We estimate the face capacity and the maximum MasterFace coverage under the assumption that identities in the face space are well separated. We conclude that MasterFaces should not be seen as a threat to face recognition systems but as a tool to enhance the robustness of face recognition models.
  arXiv  Detail & Related papers  (2022-03-23T13:02:41Z)
• Detect Faces Efficiently: A Survey and Evaluations [13.105528567365281]
  Many applications including face recognition, facial expression recognition, face tracking and head-pose estimation assume that both the location and the size of faces are known in the image. Deep learning techniques brought remarkable breakthroughs to face detection along with the price of a considerable increase in computation. This paper introduces representative deep learning-based methods and presents a deep and thorough analysis in terms of accuracy and efficiency.
  arXiv  Detail & Related papers  (2021-12-03T08:39:40Z)
• End2End Occluded Face Recognition by Masking Corrupted Features [82.27588990277192]
  State-of-the-art general face recognition models do not generalize well to occluded face images. This paper presents a novel face recognition method that is robust to occlusions based on a single end-to-end deep neural network. Our approach, named FROM (Face Recognition with Occlusion Masks), learns to discover the corrupted features from the deep convolutional neural networks, and clean them by the dynamically learned masks.
  arXiv  Detail & Related papers  (2021-08-21T09:08:41Z)
• Facial Expressions as a Vulnerability in Face Recognition [73.85525896663371]
  This work explores facial expression bias as a security vulnerability of face recognition systems. We present a comprehensive analysis of how facial expression bias impacts the performance of face recognition technologies.
  arXiv  Detail & Related papers  (2020-11-17T18:12:41Z)
• 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.