Security researchers have documented a hidden system that ships on every Mac: a pair of background processes that quietly build a detailed, queryable knowledge graph about the person using the machine and everyone around them — their contacts, their family relationships, their daily routines, even their face data — with almost no official documentation from Apple.
The analysis, published October 28 on the Eighth Rank blog by researchers Dario Pasquini and Michał Bazyli, resurfaced in a major way this week when it hit the front page of Hacker News on Friday, drawing more than 750 points and a lengthy debate about on-device privacy. Everything in the write-up was collected on macOS 26, version 26.6.2, according to the authors. For more context on this story, see our ongoing AI trends.
Two Daemons, Fifty-One Databases
The system is built by two daemons that have shipped with every Mac since macOS 13 arrived in 2022: knowledgeconstructiond and intelligenceplatformd. Apple's own documentation for the mechanism amounts to a single man page, which describes knowledgeconstructiond as a daemon that "analyzes content on this device to help build a general purpose knowledge graph" — and little more.
According to the researchers, the daemons cross-reference nearly everything the operating system can see: Contacts, Calendar, Photos (including face data), Messages and Mail, location, Screen Time, Family Sharing data — including the age of every member of a household — the Medical ID emergency contact in Health, events and contacts surfaced by Siri Suggestions, people donated by third-party apps through App Intents, and the list of installed apps.
The result lives in ~/Library/IntelligencePlatform: fifty-one SQLite databases stored in plaintext, protected from casual access by macOS's TCC Full Disk Access gate. The heart of the system is graph.db, a triple store written in a vocabulary of 181 entity classes and 278 predicates. Every row encodes a subject, a predicate and an object — a person, a relationship type, and another person, place, organization or event — with each edge carrying confidence scores, source counts and timestamps.
Your Life, Categorized
The breadth of the ontology is where the research gets striking. The researchers catalogued all 181 entity classes and found that 57 of them — nearly a third of the vocabulary — describe activities: sleeping, exercising, mindfulness sessions, going to bed, commuting, dining. Alongside the graph sit auxiliary tables recording who appears with whom in your photos and a communication log capturing who messaged whom, when, in which app, and in which direction — metadata only, without message content.
Forty-six of the predicates are relationship types that reify the edges between people, which is how the system captures not just who you know but how they relate to each other. That capability is what led Hacker News users to summarize the discovery bluntly: every Mac ships an undocumented family member classifier.
The graph is not idle metadata. The researchers describe it as a queryable store that large language models retrieve from — the substrate that lets Apple Intelligence answer questions about "my sister's photos from last summer" without sending data to the cloud. Apple's own researchers published a paper on the underlying graph-construction techniques in 2023, but the researchers note that almost nothing has been published about how the system is integrated into the shipping operating system.
Open-Sourcing a Peek — and a Warning
To let users inspect their own graphs, the researchers released iKnow, an open-source dashboard that reads the contents of ~/Library/IntelligencePlatform and renders what the system believes about you and your family.
The paper's final section is deliberately provocative. The authors run a thought experiment — which they note applies to any personalized system — showing what happens if such a knowledge base ends up in the wrong hands, combining it with an "abliterated" language model (one with safety training removed) to demonstrate how a "privacy single point of failure" can be weaponized against a user in ways that individual data leaks cannot.
The Bigger Picture
The finding lands awkwardly against the privacy-first marketing that has defined Apple's AI strategy: on-device processing is genuinely more private than cloud alternatives, but this research shows that "stays on your device" does not mean "stays small." A local system that knows your sleep schedule, your commute, your family tree and your photo history is a high-value target — whether the threat is a malicious actor with brief access to a laptop, a future software vulnerability, or an overly capable local agent prompted to misuse what it can query.
None of the data, the researchers emphasize, is transmitted off-device by the daemons themselves; the analysis concerned what is stored locally and how. But as AI assistants gain deeper access to local context, the researchers' core point stands: users were given no clear picture of what their own machines are building about them, and had to reverse-engineer the answer themselves.
---
Stay Ahead of AIGet the latest AI news, analysis, and breakthroughs — all in one place.
Read more AI news →
