# Decoding What iOS Location Services Send to Apple: An LLM Is an Unreliable Analyst but a Useful Toolmaker

> Compares direct LLM recovery of Apple PBCodable schemas with an AI-written Extractor checked against compiled synthetic fixtures, published descriptors and captured traffic. It shows how plausible recovered schemas can silently decode values incorrectly.

- Authors: Douglas Leith
- Venue: arXiv
- Status: Preprint
- Publication / posting date: October 15, 2026
- Date source: First arXiv submission; the reviewed version is v1, not a verified proceedings publication.
- First arXiv submission: October 15, 2026
- arXiv: 2610.21597
- Reviewed arXiv version: v1
- Sources reviewed: 2026-10-20
- Added to the catalog: 2026-10-20
- Original paper: <https://arxiv.org/abs/2610.21597>
- PDF: <https://arxiv.org/pdf/2610.21597v1>
- Code: <https://github.com/doug-leith/ios-protobuf-decoding>
- BibTeX: <https://awesomerea.org/papers/citations/paper-ios-protobuf-extractor.bib>
- Catalog page: <https://awesomerea.org/papers/paper-ios-protobuf-extractor/>
- Record JSON: <https://awesomerea.org/papers/paper-ios-protobuf-extractor/record.json>
- Chinese version: [简体中文](https://awesomerea.org/zh/papers/paper-ios-protobuf-extractor/index.md)

## Scope and limitations

The direct-agent study uses 17 seeds with 7,788 field occurrences, 4,987 distinct. Apple's true schemas remain unpublished; synthetic tests share the recovered template's assumptions. Traffic comes from one jailbroken iPhone 8 on iOS 16.7.11. Matching fields in newer OS binaries does not verify their network behavior. The maintained code also documents estimated or unresolved fields.

## Why it fits this collection

A concrete binary-to-protocol-schema recovery study that separates parseable output from verified interpretation.

## Publication and review notes

ArXiv names Douglas Leith; the manuscript uses D.J. Leith. No repository-wide license was verified.

## Primary sources

1. <https://arxiv.org/abs/2610.21597>
2. <https://arxiv.org/html/2610.21597v1>
3. <https://github.com/doug-leith/ios-protobuf-decoding/blob/9a4a688c52686f82c1a86e386848edc4eb671746/README.md>
4. <https://github.com/doug-leith/ios-location-services-study-data/blob/a091d8dad932faf7e8e526ef07b854640ce8bc23/README.md>

## About this entry

Reviewed against the paper and its primary sources. Cite the original authors using the linked paper or BibTeX.
Original editorial content: MIT. Linked projects, papers and assets retain their own rights and licenses.