Key-Nets: Optical Transformation Convolutional Networks for Privacy Preserving Vision Sensors

• URL: http://arxiv.org/abs/2008.04469v2
• Date: Fri, 11 Sep 2020 13:50:29 GMT
• Title: Key-Nets: Optical Transformation Convolutional Networks for Privacy Preserving Vision Sensors
• Authors: Jeffrey Byrne and Brian DeCann and Scott Bloom
• Abstract summary: Key-nets are convolutional networks paired with a custom vision sensor. We show that a key-net is equivalent to homomorphic encryption using a Hill cipher.
• Score: 3.3517146652431378
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern cameras are not designed with computer vision or machine learning as the target application. There is a need for a new class of vision sensors that are privacy preserving by design, that do not leak private information and collect only the information necessary for a target machine learning task. In this paper, we introduce key-nets, which are convolutional networks paired with a custom vision sensor which applies an optical/analog transform such that the key-net can perform exact encrypted inference on this transformed image, but the image is not interpretable by a human or any other key-net. We provide five sufficient conditions for an optical transformation suitable for a key-net, and show that generalized stochastic matrices (e.g. scale, bias and fractional pixel shuffling) satisfy these conditions. We motivate the key-net by showing that without it there is a utility/privacy tradeoff for a network fine-tuned directly on optically transformed images for face identification and object detection. Finally, we show that a key-net is equivalent to homomorphic encryption using a Hill cipher, with an upper bound on memory and runtime that scales quadratically with a user specified privacy parameter. Therefore, the key-net is the first practical, efficient and privacy preserving vision sensor based on optical homomorphic encryption.

Related papers

• Can Encrypted Images Still Train Neural Networks? Investigating Image Information and Random Vortex Transformation [51.475827684468875]
  We establish a novel framework for measuring image information content to evaluate the variation in information content during image transformations. We also propose a novel image encryption algorithm called Random Vortex Transformation.
  arXiv  Detail & Related papers  (2024-11-25T09:14:53Z)
• 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)
• Human-imperceptible, Machine-recognizable Images [76.01951148048603]
  A major conflict is exposed relating to software engineers between better developing AI systems and distancing from the sensitive training data. This paper proposes an efficient privacy-preserving learning paradigm, where images are encrypted to become human-imperceptible, machine-recognizable'' We show that the proposed paradigm can ensure the encrypted images have become human-imperceptible while preserving machine-recognizable information.
  arXiv  Detail & Related papers  (2023-06-06T13:41:37Z)
• 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)
• EViT: Privacy-Preserving Image Retrieval via Encrypted Vision Transformer in Cloud Computing [9.41257807502252]
  We propose a novel paradigm named Encrypted Vision Transformer (EViT), which advances the discriminative representations capability of cipher-images. EViT achieves both excellent encryption and retrieval performance, outperforming current schemes in terms of retrieval accuracy by large margins while protecting image privacy effectively.
  arXiv  Detail & Related papers  (2022-08-31T07:07:21Z)
• An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applications [15.206936859511]
  Learnable image encryption is applicable to privacy-preserving machine learning and adversarially robust defense. This article presents an overview of image transformation with a secret key and its applications.
  arXiv  Detail & Related papers  (2022-01-26T15:29:51Z)
• Speckle-based optical cryptosystem and its application for human face recognition via deep learning [17.169570487230747]
  Face images are sensitive biometric data that should be carefully protected. In this study, a plain yet high-efficient speckle-based optical cryptosystem is proposed and implemented. The proposed cryptosystem has wide applicability, and it may open a new avenue for high-security complex information encryption and decryption.
  arXiv  Detail & Related papers  (2022-01-26T07:18:02Z)
• Semantic-Aware Generation for Self-Supervised Visual Representation Learning [116.5814634936371]
  We advocate for Semantic-aware Generation (SaGe) to facilitate richer semantics rather than details to be preserved in the generated image. SaGe complements the target network with view-specific features and thus alleviates the semantic degradation brought by intensive data augmentations. We execute SaGe on ImageNet-1K and evaluate the pre-trained models on five downstream tasks including nearest neighbor test, linear classification, and fine-scaled image recognition.
  arXiv  Detail & Related papers  (2021-11-25T16:46:13Z)
• Privacy-Preserving Image Acquisition Using Trainable Optical Kernel [50.1239616836174]
  We propose a trainable image acquisition method that removes the sensitive identity revealing information in the optical domain before it reaches the image sensor. As the sensitive content is suppressed before it reaches the image sensor, it does not enter the digital domain therefore is unretrievable by any sort of privacy attack.
  arXiv  Detail & Related papers  (2021-06-28T11:08:14Z)

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.