Fairness Properties of Face Recognition and Obfuscation Systems

• URL: http://arxiv.org/abs/2108.02707v1
• Date: Thu, 5 Aug 2021 16:18:15 GMT
• Title: Fairness Properties of Face Recognition and Obfuscation Systems
• Authors: Harrison Rosenberg, Brian Tang, Kassem Fawaz, and Somesh Jha
• Abstract summary: Face obfuscation systems generate imperceptible perturbations, when added to an image, cause the facial recognition system to misidentify the user. This dependence of face obfuscation on metric embedding networks, which are known to be unfair in the context of facial recognition, surfaces the question of demographic fairness. We find that metric embedding networks are demographically aware; they cluster faces in the embedding space based on their demographic attributes.
• Score: 19.195705814819306
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The proliferation of automated facial recognition in various commercial and government sectors has caused significant privacy concerns for individuals. A recent and popular approach to address these privacy concerns is to employ evasion attacks against the metric embedding networks powering facial recognition systems. Face obfuscation systems generate imperceptible perturbations, when added to an image, cause the facial recognition system to misidentify the user. The key to these approaches is the generation of perturbations using a pre-trained metric embedding network followed by their application to an online system, whose model might be proprietary. This dependence of face obfuscation on metric embedding networks, which are known to be unfair in the context of facial recognition, surfaces the question of demographic fairness -- \textit{are there demographic disparities in the performance of face obfuscation systems?} To address this question, we perform an analytical and empirical exploration of the performance of recent face obfuscation systems that rely on deep embedding networks. We find that metric embedding networks are demographically aware; they cluster faces in the embedding space based on their demographic attributes. We observe that this effect carries through to the face obfuscation systems: faces belonging to minority groups incur reduced utility compared to those from majority groups. For example, the disparity in average obfuscation success rate on the online Face++ API can reach up to 20 percentage points. Further, for some demographic groups, the average perturbation size increases by up to 17\% when choosing a target identity belonging to a different demographic group versus the same demographic group. Finally, we present a simple analytical model to provide insights into these phenomena.

Related papers

• Privacy-Preserving Face Recognition in Hybrid Frequency-Color Domain [16.05230409730324]
  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.
  arXiv  Detail & Related papers  (2024-01-24T11:27:32Z)
• 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)
• Robustness Disparities in Face Detection [64.71318433419636]
  We present the first of its kind detailed benchmark of face detection systems, specifically examining the robustness to noise of commercial and academic models. Across all the datasets and systems, we generally find that photos of individuals who are $textitmasculine presenting$, of $textitolder$, of $textitdarker skin type$, or have $textitdim lighting$ are more susceptible to errors than their counterparts in other identities.
  arXiv  Detail & Related papers  (2022-11-29T05:22:47Z)
• My Face My Choice: Privacy Enhancing Deepfakes for Social Media Anonymization [4.725675279167593]
  We introduce three face access models in a hypothetical social network, where the user has the power to only appear in photos they approve. Our approach eclipses current tagging systems and replaces unapproved faces with quantitatively dissimilar deepfakes. Running seven SOTA face recognizers on our results, MFMC reduces the average accuracy by 61%.
  arXiv  Detail & Related papers  (2022-11-02T17:58:20Z)
• Towards Intrinsic Common Discriminative Features Learning for Face Forgery Detection using Adversarial Learning [59.548960057358435]
  We propose a novel method which utilizes adversarial learning to eliminate the negative effect of different forgery methods and facial identities. Our face forgery detection model learns to extract common discriminative features through eliminating the effect of forgery methods and facial identities.
  arXiv  Detail & Related papers  (2022-07-08T09:23:59Z)
• 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)
• Mitigating Face Recognition Bias via Group Adaptive Classifier [53.15616844833305]
  This work aims to learn a fair face representation, where faces of every group could be more equally represented. Our work is able to mitigate face recognition bias across demographic groups while maintaining the competitive accuracy.
  arXiv  Detail & Related papers  (2020-06-13T06:43:37Z)
• SensitiveLoss: Improving Accuracy and Fairness of Face Representations with Discrimination-Aware Deep Learning [17.088716485755917]
  We propose a discrimination-aware learning method to improve accuracy and fairness of biased face recognition algorithms. We experimentally show that learning processes based on the most used face databases have led to popular pre-trained deep face models that present a strong algorithmic discrimination. Our approach works as an add-on to pre-trained networks and is used to improve their performance in terms of average accuracy and fairness.
  arXiv  Detail & Related papers  (2020-04-22T10:32:16Z)
• 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.