Star on GitHubStar3.2k stars

2026 · Preprint

SEMPRE: Semantic-Aware Protocol Reverse Engineering via Consistency-Driven Joint Optimization

SEMPRE uses dynamic analysis and LLM reasoning to recover hierarchical message fields, infer their types and roles, and refine field boundaries. It evaluates the method on mainstream protocols and a botnet case study.

Scope and limitations

The evaluation covers mainstream protocols, comparisons with six baselines, component ablations, and a botnet case study.

Why it fits this collection

Inferring undocumented protocol message layouts and field meanings is protocol reverse engineering.

Cite

@misc{paper-sempre,
  title = {{SEMPRE: Semantic-Aware Protocol Reverse Engineering via Consistency-Driven Joint Optimization}},
  author = {{Yihua Xu} and {Weijie Huang} and {Xiaofeng Wang} and {Hang Zhang} and {Binghui Wang} and {Yue Duan}},
  year = {2026},
  url = {https://arxiv.org/abs/2610.31844},
  howpublished = {arXiv:2610.31844},
  note = {Preprint},
  eprint = {2610.31844},
  archivePrefix = {arXiv},
  month = oct
}

Read in a terminal: hf papers read 2610.31844

Publication and review details

Venue
arXiv
Status
Preprint
Publication / posting date
October 22, 2026
Date source
First arXiv submission date.
First arXiv submission
October 22, 2026
arXiv
2610.31844
Reviewed arXiv version
v1

The date and venue come from the arXiv record.

Sources reviewed

Reviewed against the paper and its primary sources. Cite the original authors using the linked paper or BibTeX.

Report an outdated entry Suggest a translation fix

Primary sources

  1. https://arxiv.org/abs/2610.31844
↑↓ move↵ open⌘↵ new tab