What is SeePrivacy?
Privacy policies have become the most critical approach to safeguarding individuals' privacy and digital security.
To enhance their presentation and readability, the concept of Contextual Privacy Policies (CPPs) was gradually developed,
aiming to fragment policies into shorter snippets and display them only in corresponding contexts.
We are the first to propose a novel multi-modal framework, namely SeePrivacy, designed to automatically generate contextual privacy policies for mobile apps.
Our framework does not require the access to apps' source code or Android APIs; hence, the framework can be easily deployed with lower security concerns.
What can SeePrivacy bring to you?
Overview of SeePrivacy
The framework synergistically combines CV-based mobile GUI understanding and NLP-based privacy policy document analysis.
Functionality and Usability
SeePrivacy achieves 0.88 precision and 0.90 recall to detect contexts; as
well as 0.98 precision and 0.96 recall to extract corresponding policy segments.
The user study shows SeePrivacy demonstrates excellent functionality and usability (4.5/5).
Specifically, participants exhibit a greater willingness to read CPPs (4.1/5) compared to original privacy policies (2/5).
In conclusion, our solution effectively assists users in comprehending privacy notices, and this research establishes a solid foundation for further advancements and exploration.
Welcome to cite us:
@misc{pan2023seeprivacy,
title={SeePrivacy: Automated Contextual Privacy Policy Generation for Mobile Applications},
author={Shidong Pan and Zhen Tao and Thong Hoang and Dawen Zhang and Zhenchang Xing and Xiwei Xu and Mark Staples and David Lo},
year={2023},
eprint={2307.01691},
archivePrefix={arXiv},
primaryClass={cs.CR}
}