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

arXiv: https://arxiv.org/abs/2008.04469 · HTML: https://mlsanity.com/paper/2008.04469/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Aug 2020.

## Built on by (most cited first, 3 of 3)

- [Fine-grained Activities of People Worldwide](https://mlsanity.com/paper/2207.05182/) (2022)
- [The Need for Inherently Privacy-Preserving Vision in Trustworthy Autonomous Systems](https://mlsanity.com/paper/2303.16408/) (2023)
- [Privacy-Preserving Deep Learning Using Deformable Operators for Secure Task Learning](https://mlsanity.com/paper/2404.05828/) (2024)

## Abstract (arXiv)

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.