# Privacy-Preserving Semantic Segmentation without Key Management

Source: [Privacy-Preserving Semantic Segmentation without Key Management](<https://www.sota2.com/research/paper/69e704907d0172140ec7ece3>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-22T05:21:28.943Z

Authors: Mare Hirose, Shoko Imaizumi, Hitoshi Kiya

Published: 2026-04-16T10:45:58.000Z

## Abstract

This paper proposes a novel privacy-preserving semantic segmentation method that can use independent keys for each client and image. In the proposed method, the model creator and each client encrypt images using locally generated keys, and model training and inference are conducted on the encrypted images. To mitigate performance degradation, an image encryption method is applied to model training in addition to the generation of test images. In experiments, the effectiveness of the proposed method is confirmed on the Cityscapes dataset under the use of a vision transformer-based model, called SETR.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.16523>)

[PDF](<https://arxiv.org/pdf/2604.16523.pdf>)