Privacy in Eye Tracking Research with Stable Diffusion
K. Kurzhals. Proceedings of the 2023 Symposium on Eye Tracking Research and Applications, page 1–7. New York, NY, USA, Association for Computing Machinery, (May 30, 2023)
DOI: 10.1145/3588015.3589842
Abstract
Image-generative models take textual prompts as input and generate almost arbitrary image content based on the underlying training data. This technology is rapidly developing and produces better results with each new generation of trained models. Apart from the application to create artwork, we see potential in deploying such models for eye-tracking research with respect to anonymizing content in visual stimuli. One feature of such models is the ability to take an image as input and adjust content according to a prompt. Hence, privacy-preserving visualization of stimuli can be achieved for static images and videos by slightly adjusting content to anonymize persons, text, and other sensible sources. In this work, we will discuss how this process can be applied to the presentation and dissemination of results with respect to privacy issues resulting from eye-tracking experiments.
%0 Conference Paper
%1 Kurzhals2023
%A Kurzhals, Kuno
%B Proceedings of the 2023 Symposium on Eye Tracking Research and Applications
%C New York, NY, USA
%D 2023
%I Association for Computing Machinery
%K myown peer rp28 from:kurzhako visus:kurzhako rp28-1
%P 1–7
%R 10.1145/3588015.3589842
%T Privacy in Eye Tracking Research with Stable Diffusion
%U https://doi.org/10.1145/3588015.3589842
%X Image-generative models take textual prompts as input and generate almost arbitrary image content based on the underlying training data. This technology is rapidly developing and produces better results with each new generation of trained models. Apart from the application to create artwork, we see potential in deploying such models for eye-tracking research with respect to anonymizing content in visual stimuli. One feature of such models is the ability to take an image as input and adjust content according to a prompt. Hence, privacy-preserving visualization of stimuli can be achieved for static images and videos by slightly adjusting content to anonymize persons, text, and other sensible sources. In this work, we will discuss how this process can be applied to the presentation and dissemination of results with respect to privacy issues resulting from eye-tracking experiments.
%@ 9798400701504
@inproceedings{Kurzhals2023,
abstract = {Image-generative models take textual prompts as input and generate almost arbitrary image content based on the underlying training data. This technology is rapidly developing and produces better results with each new generation of trained models. Apart from the application to create artwork, we see potential in deploying such models for eye-tracking research with respect to anonymizing content in visual stimuli. One feature of such models is the ability to take an image as input and adjust content according to a prompt. Hence, privacy-preserving visualization of stimuli can be achieved for static images and videos by slightly adjusting content to anonymize persons, text, and other sensible sources. In this work, we will discuss how this process can be applied to the presentation and dissemination of results with respect to privacy issues resulting from eye-tracking experiments.},
added-at = {2023-06-26T08:24:17.000+0200},
address = {New York, NY, USA},
author = {Kurzhals, Kuno},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/23cd1d4babeb4bb3cdda00d133bd24691/intcdc},
booktitle = {Proceedings of the 2023 Symposium on Eye Tracking Research and Applications},
day = 30,
doi = {10.1145/3588015.3589842},
interhash = {2c87701323327b3396dd01b02ff239cf},
intrahash = {3cd1d4babeb4bb3cdda00d133bd24691},
isbn = {9798400701504},
keywords = {myown peer rp28 from:kurzhako visus:kurzhako rp28-1},
location = {Tubingen, Germany},
month = {5},
pages = {1–7},
publisher = {Association for Computing Machinery},
series = {ETRA '23},
timestamp = {2023-06-26T08:24:17.000+0200},
title = {Privacy in Eye Tracking Research with Stable Diffusion},
url = {https://doi.org/10.1145/3588015.3589842},
year = 2023
}
