Explain to me: Towards understanding privacy decisions
Type :
Conference paper
Publication Status :
Published
Access :
restrictedAccess
Abstract
Privacy assistants help users manage their privacy online. Their tasks could vary from detecting privacy violations to recommending sharing actions for content that the user intends to share. Recent work on these tasks are promising and show that privacy assistants can successfully tackle them. However, for such privacy assistants to be employed by users, it is important that these assistants can explain their decisions to users. Accordingly, this work develops a methodology to create explanations of privacy. The methodology is based on identifying important topics in a domain of interest, providing explanation schemes for decisions, and generating them automatically. We apply our proposed methodology on a real-world privacy data set, which contains images labeled as private or public to explain the labels.
Source :
Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
Date :
2023
Publisher :
International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
URI
http://hdl.handle.net/10679/9072https://www.ifaamas.org/Proceedings/aamas2023/forms/contents.htm
Collections
Share this page