Skip to main navigation Skip to search Skip to main content

A Demonstration of PKGem: Secure Enrichment of Personal Knowledge Graphs

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We present PKGem, a system that provides an end-to-end secure solution to enrich personal knowledge graphs in mobile environments. This task faces two core challenges: First, the proprietary, user-centric, and locally stored nature of personal knowledge graphs makes collaborative enrichment with socially connected peers a privacy concern. Moreover, the mobile environment has strict constraints on resource and computation cost, requiring lightweight and efficient design. PKGem addresses both challenges by leveraging cryptographic techniques to enable secure data enrichment across personal knowledge graphs, while remaining practical under mobile constraints. The system is implemented as an Android application and supports a variety of real-world usage scenarios. The code of PKGem is available at https://github.com/golden-eggs-lab/pkgem, with a demonstration video link included in the repository.

Original languageEnglish (US)
Title of host publicationCIKM 2025 - Proceedings of the 34th ACM International Conference on Information and Knowledge Management
PublisherAssociation for Computing Machinery, Inc
Pages6708-6712
Number of pages5
ISBN (Electronic)9798400720406
DOIs
StatePublished - Nov 10 2025
Event34th ACM International Conference on Information and Knowledge Management, CIKM 2025 - Seoul, Korea, Republic of
Duration: Nov 10 2025 → Nov 14 2025

Publication series

NameCIKM 2025 - Proceedings of the 34th ACM International Conference on Information and Knowledge Management

Conference

Conference34th ACM International Conference on Information and Knowledge Management, CIKM 2025
Country/TerritoryKorea, Republic of
CitySeoul
Period11/10/25 → 11/14/25

Bibliographical note

Publisher Copyright:
© 2025 Copyright held by the owner/author(s).

Keywords

  • entity resolution
  • fully homomorphic encryption
  • knowledge graph

Fingerprint

Dive into the research topics of 'A Demonstration of PKGem: Secure Enrichment of Personal Knowledge Graphs'. Together they form a unique fingerprint.

Cite this