Master Face Attacks on Face Recognition Systems

• URL: http://arxiv.org/abs/2109.03398v1
• Date: Wed, 8 Sep 2021 02:11:35 GMT
• Title: Master Face Attacks on Face Recognition Systems
• Authors: Huy H. Nguyen, S\'ebastien Marcel, Junichi Yamagishi, Isao Echizen
• Abstract summary: Face authentication is now widely used, especially on mobile devices, rather than authentication using a personal identification number or an unlock pattern. Previous work has proven the existence of master faces that match multiple enrolled templates in face recognition systems. In this paper, we perform an extensive study on latent variable evolution (LVE), a method commonly used to generate master faces.
• Score: 45.090037010778765
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Face authentication is now widely used, especially on mobile devices, rather than authentication using a personal identification number or an unlock pattern, due to its convenience. It has thus become a tempting target for attackers using a presentation attack. Traditional presentation attacks use facial images or videos of the victim. Previous work has proven the existence of master faces, i.e., faces that match multiple enrolled templates in face recognition systems, and their existence extends the ability of presentation attacks. In this paper, we perform an extensive study on latent variable evolution (LVE), a method commonly used to generate master faces. We run an LVE algorithm for various scenarios and with more than one database and/or face recognition system to study the properties of the master faces and to understand in which conditions strong master faces could be generated. Moreover, through analysis, we hypothesize that master faces come from some dense areas in the embedding spaces of the face recognition systems. Last but not least, simulated presentation attacks using generated master faces generally preserve the false-matching ability of their original digital forms, thus demonstrating that the existence of master faces poses an actual threat.

Related papers

• LAFS: Landmark-based Facial Self-supervised Learning for Face Recognition [37.4550614524874]
  We focus on learning facial representations that can be adapted to train effective face recognition models. We explore the learning strategy of unlabeled facial images through self-supervised pretraining. Our method achieves significant improvement over the state-of-the-art on multiple face recognition benchmarks.
  arXiv  Detail & Related papers  (2024-03-13T01:07:55Z)
• 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)
• Digital and Physical Face Attacks: Reviewing and One Step Further [31.780516471483985]
  Face presentation attacks (FPA) have raised pressing mistrust concerns. Besides physical face attacks, face videos/images are vulnerable to a wide variety of digital attack techniques launched by malicious hackers. This survey aims to build the integrity of face forensics by providing thorough analyses of existing literature and highlighting the issues requiring further attention.
  arXiv  Detail & Related papers  (2022-09-29T11:25:52Z)
• 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)
• Generating Master Faces for Dictionary Attacks with a Network-Assisted Latent Space Evolution [68.8204255655161]
  A master face is a face image that passes face-based identity-authentication for a large portion of the population. We optimize these faces, by using an evolutionary algorithm in the latent embedding space of the StyleGAN face generator.
  arXiv  Detail & Related papers  (2021-08-01T12:55:23Z)
• Generating Master Faces for Use in Performing Wolf Attacks on Face Recognition Systems [40.59670229362299]
  Face authentication has become increasingly mainstream and is now a prime target for attackers. Previous research has shown that finger-vein- and fingerprint-based authentication methods are susceptible to wolf attacks. We generated high-quality master faces by using the state-of-the-art face generator StyleGAN.
  arXiv  Detail & Related papers  (2020-06-15T12:59:49Z)
• 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.