Researchers detail macOS daemons that build a personal relationship graph from device data
Security researchers examined two undocumented macOS background processes, knowledgeconstructiond and intelligenceplatformd, which have run on Macs since 2022 and build a queryable knowledge graph of a user's contacts, calendar, photos, messages, mail, location and screen-time data. Apple's only public documentation is a terse man page, and the researchers say the system can infer kinship and relationships between people, a feature not previously described publicly. They note Apple published a 2023 research paper on the underlying graph-construction techniques but has not disclosed how it operates inside macOS or exactly what data it collects and infers.
GoKawiil's interpretation of the reporting above, not reported fact.
The findings suggest Apple Intelligence features may rely on far more extensive on-device profiling than users are aware of, raising questions about transparency even when data stays local rather than reaching the cloud. Because the graph reportedly infers relationships like kinship from behavioral signals, it could expose sensitive social information that wasn't explicitly provided by the user, which privacy researchers may scrutinize further. The lack of documentation also means third-party developers and security auditors have had to reverse-engineer the system rather than rely on official specs.
- Two little-documented macOS daemons, knowledgeconstructiond and intelligenceplatformd, build a personal knowledge graph from on-device data since 2022.
- The graph reportedly cross-references Contacts, Calendar, Photos, Messages, Mail, location and Screen Time, and can infer relationships like kinship.
- Apple has published academic research on the underlying technique but has not documented how it functions within macOS or what exactly it stores and infers.
Source: 8rank.ai, 2026-11-07
Published there as: “Every Mac comes with an (undocumented) family member classifier”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.