mlsanityData to 14 Oct 2026

An Access Control Method with Secret Key for Semantic Segmentation Models

arXiv 2208.13135 ↗First posted 28 Aug 2022cs.CV cs.CR cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

A novel method for access control with a secret key is proposed to protect models from unauthorized access in this paper. We focus on semantic segmentation models with the vision transformer (ViT), called segmentation transformer (SETR). Most existing access control methods focus on image classification tasks, or they are limited to CNNs. By using a patch embedding structure that ViT has, trained models and test images can be efficiently encrypted with a secret key, and then semantic segmentation tasks are carried out in the encrypted domain. In an experiment, the method is confirmed to provide the same accuracy as that of using plain images without any encryption to authorized users with a correct key and also to provide an extremely degraded accuracy to unauthorized users.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 22 references that are in the map. First posted on arXiv 28 Aug 2022.

Builds on

15 of 22 references.

References · 15

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  4. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
  5. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 357
  6. 2017Embedding Watermarks into Deep Neural Networkscited by 248
  7. 2019Recent Advances in Deep Learning for Object Detectioncited by 50
  8. 2022An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applicationscited by 29
  9. 2022Privacy-Preserving Image Classification Using Isotropic Networkcited by 17
  10. 2021A Protection Method of Trained CNN Model with Secret Key from Unauthorized Accesscited by 15
  11. 2022Image and Model Transformation with Secret Key for Vision Transformercited by 12
  12. 2021Piracy-Resistant DNN Watermarking by Block-Wise Image Transformation with Secret Keycited by 10
3 more
  1. 2021Access Control Using Spatially Invariant Permutation of Feature Maps for Semantic Segmentation Modelscited by 4
  2. 2022Access Control of Semantic Segmentation Models Using Encrypted Feature Mapscited by 3
  3. 2022Access Control of Object Detection Models Using Encrypted Feature Mapscited by 1

Built on by

Not cited yet.