A Study of Face Obfuscation in ImageNet

• URL: http://arxiv.org/abs/2103.06191v1
• Date: Wed, 10 Mar 2021 17:11:34 GMT
• Title: A Study of Face Obfuscation in ImageNet
• Authors: Kaiyu Yang, Jacqueline Yau, Li Fei-Fei, Jia Deng, Olga Russakovsky
• Abstract summary: In this paper, we explore image obfuscation in the ImageNet challenge. Most categories in the ImageNet challenge are not people categories; nevertheless, many incidental people are in the images. We benchmark various deep neural networks on face-blurred images and observe a disparate impact on different categories. Results show that features learned on face-blurred images are equally transferable.
• Score: 94.2949777826947
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image obfuscation (blurring, mosaicing, etc.) is widely used for privacy protection. However, computer vision research often overlooks privacy by assuming access to original unobfuscated images. In this paper, we explore image obfuscation in the ImageNet challenge. Most categories in the ImageNet challenge are not people categories; nevertheless, many incidental people are in the images, whose privacy is a concern. We first annotate faces in the dataset. Then we investigate how face blurring -- a typical obfuscation technique -- impacts classification accuracy. We benchmark various deep neural networks on face-blurred images and observe a disparate impact on different categories. Still, the overall accuracy only drops slightly ($\leq 0.68\%$), demonstrating that we can train privacy-aware visual classifiers with minimal impact on accuracy. Further, we experiment with transfer learning to 4 downstream tasks: object recognition, scene recognition, face attribute classification, and object detection. Results show that features learned on face-blurred images are equally transferable. Data and code are available at https://github.com/princetonvisualai/imagenet-face-obfuscation.

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 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)
• 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)
• MorDeephy: Face Morphing Detection Via Fused Classification [0.0]
  We introduce a novel deep learning strategy for a single image face morphing detection. It is directed onto learning the deep facial features, which carry information about the authenticity of these features. Our method, which we call MorDeephy, achieved the state of the art performance and demonstrated a prominent ability for generalising the task of morphing detection to unseen scenarios.
  arXiv  Detail & Related papers  (2022-08-05T11:39:22Z)
• LFW-Beautified: A Dataset of Face Images with Beautification and Augmented Reality Filters [53.180678723280145]
  We contribute with a database of facial images that includes several manipulations. It includes image enhancement filters (which mostly modify contrast and lightning) and augmented reality filters that incorporate items like animal noses or glasses. Each dataset contains 4,324 images of size 64 x 64, with a total of 34,592 images.
  arXiv  Detail & Related papers  (2022-03-11T17:05:10Z)
• DeepBlur: A Simple and Effective Method for Natural Image Obfuscation [4.80165284612342]
  We present DeepBlur, a simple yet effective method for image obfuscation by blurring in the latent space of an unconditionally pre-trained generative model. We compare it with existing methods by efficiency and image quality, and evaluate against both state-of-the-art deep learning models and industrial products.
  arXiv  Detail & Related papers  (2021-03-31T19:31:26Z)
• InfoScrub: Towards Attribute Privacy by Targeted Obfuscation [77.49428268918703]
  We study techniques that allow individuals to limit the private information leaked in visual data. We tackle this problem in a novel image obfuscation framework. We find our approach generates obfuscated images faithful to the original input images, and additionally increase uncertainty by 6.2$times$ (or up to 0.85 bits) over the non-obfuscated counterparts.
  arXiv  Detail & Related papers  (2020-05-20T19:48:04Z)
• 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)
• PrivacyNet: Semi-Adversarial Networks for Multi-attribute Face Privacy [15.301150389512744]
  We develop a technique for soft biometric privacy to face images via an image methodology. The image perturbation is undertaken using a GAN-based Semi-Adversarial Network (SAN) PrivacyNet allows a person to choose attributes that have to be obfuscated in the input face images.
  arXiv  Detail & Related papers  (2020-01-02T18:53:31Z)

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.