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

08/11/2020
by   Jeffrey Byrne, et al.
9

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.

READ FULL TEXT

page 6

page 9

page 18

page 19

page 20

page 23

page 25

research
04/28/2020

Attacks on Image Encryption Schemes for Privacy-Preserving Deep Neural Networks

Privacy preserving machine learning is an active area of research usuall...
research
04/29/2019

HOG feature extraction from encrypted images for privacy-preserving machine learning

In this paper, we propose an extraction method of HOG (histograms-of-ori...
research
01/26/2022

An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applications

This article presents an overview of image transformation with a secret ...
research
05/26/2022

To image, or not to image: Class-specific diffractive cameras with all-optical erasure of undesired objects

Privacy protection is a growing concern in the digital era, with machine...
research
12/25/2022

Data class-specific all-optical transformations and encryption

Diffractive optical networks provide rich opportunities for visual compu...
research
03/11/2021

Privacy-preserving Object Detection

Privacy considerations and bias in datasets are quickly becoming high-pr...

Please sign up or login with your details

Forgot password? Click here to reset