arXiv cs.AI· Douglas Leith·· 2 天前AI 评分34
研究：LLM 逆向 iPhone 定位服务 protobuf 不可靠，但能造出可靠工具 Extractor
Decoding What iOS Location Services Send to Apple: An LLM Is an Unreliable Analyst but a Useful Toolmaker
AI 导读
研究用 Claude Opus 4.8 和 Codex GPT Sol 5.6 从 Apple 二进制文件中重建 iPhone 定位服务 protobuf 的 schema，发现绝大多数 schema 存在大量错误，且因内部自洽而难以察觉，不适合直接用于取证与隐私分析。
正文 · 原文
Abstract:Reverse engineering the data formats used by mobile software is skilled and slow, and using AI to assist with it is attractive. We evaluate this for the protobuf messages that an iPhone sends to Apple's location services. Working from Apple's binaries, we use two frontier models (Claude Opus 4.8, Codex GPT Sol 5.6) to reconstruct the schemas of protobufs observed in network traffic. The great majority of the schemas contain substantial errors, and these are hard to detect because the schemas are internally consistent. Direct AI use is therefore unsuitable for forensic and privacy analysis. AI can, however, write reliable analysis tools when their output can be validated. We use Claude to write a Python tool, Extractor, that reliably recovers protobuf schemas from Apple binaries. We validate it against binaries compiled from schemas with known answers, previously published schemas, and network measurements. We demonstrate the use of Extractor to decode and analyse the location services network traffic of a jailbroken iPhone 8 (iOS 16.7.11).
| Subjects: | Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.21597 [cs.NI] |
| (or arXiv:2610.21597v1 [cs.NI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21597 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Douglas Leith [view email]
[v1]
Thu, 15 Oct 2026 09:43:26 UTC (559 KB)
来源：arXiv cs.AI · arxiv.org