# Protocol Reverse Engineering via Deep Transfer Learning

> Transfers field-boundary patterns from standardized protocol traces labeled by Tshark to poorly documented target protocols. A source-selection stage chooses related protocols, and a neural domain-adaptation model infers message syntax from their shared patterns.

- Authors: Yanyang Zhao; Zhengxiong Luo; Wenlong Zhang; Feifan Wu; Yuanliang Chen; Fuchen Ma; Qi Xu; Heyuan Shi; Yu Jiang
- Venue: Proceedings of the ACM on Software Engineering / FSE 2026
- Status: Journal article
- Publication / posting date: June 30, 2026
- Date source: ACM-deposited Crossref print/online publication date; the author-hosted manuscript retains placeholder publication metadata.
- DOI: 10.1145/3797124
- Sources reviewed: 2026-10-20
- Added to the catalog: 2026-10-20
- Original paper: <https://doi.org/10.1145/3797124>
- PDF: <https://dl.acm.org/doi/pdf/10.1145/3797124>
- BibTeX: <https://awesomerea.org/papers/citations/paper-transre.bib>
- Catalog page: <https://awesomerea.org/papers/paper-transre/>
- Record JSON: <https://awesomerea.org/papers/paper-transre/record.json>
- Chinese version: [简体中文](https://awesomerea.org/zh/papers/paper-transre/index.md)

## Scope and limitations

Recovers message syntax, not state transitions. Evaluation uses 12 protocol variants; payload noise can distort source selection, while encrypted, compressed or obfuscated traffic needs separate preprocessing. Camera experiments supplement format metrics, but the four reported issues were vendor-known and do not establish complete protocol recovery.

## Why it fits this collection

Adds a transfer-learning approach to recovering undocumented message formats without parser source code.

## Publication and review notes

June 2026 is a strong six-month-window supplement. Fulltext was read from the public PDF explicitly linked by coauthor Fuchen Ma; its February date and placeholder DOI are not used as final metadata. The publisher PDF previously returned 403. Crossref confirms nine authors, volume 3(FSE), pages 636–656 and CC BY 4.0 for the version of record. No author-linked implementation release or code license was verified.

## Primary sources

1. <https://api.crossref.org/works/10.1145/3797124>
2. <https://fcorleone.github.io/publications/>
3. <https://conf.researchr.org/details/fse-2026/fse-2026-research-papers/77/Protocol-Reverse-Engineering-via-Deep-Transfer-Learning>

## 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.