EUVIMEDEUVIMED entdecken
Studienprotokoll

EBPFI: enhancing binary protocol format inference via field boundary learning

Zhen Wang, Sen Zhao, Yibo Qu, Xiurong Cao, Rongrong Xi, Lun Li, Hongsong Zhu

The Computer Journal · 15.11.2026 · 69 (11) · 1878-1890

DOI: 10.1093/comjnl/bxag065 ↗

Kurz gefasst

Studienprotokoll in der Zeitschrift The Computer Journal, online erschienen am 25.06.2026. Verfasst von Zhen Wang und 6 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Protocol reverse engineering can be applied to various security applications, including fuzzing, malware analysis, and intrusion detection. It aims to acquire an unknown protocol’s format and semantics, where format extraction is the primary task. Currently, there are already methods such as multiple sequence comparison, statistical analysis, and deep learning to extract field formats from network traffic. However, they mainly locate key fields and learn boundary information through heuristic rules or comparative analysis, and they have limitations in processing large datasets and generalization inference. This paper proposes EBPFI, a novel framework that integrates deep learning with self-supervised boundary learning to enhance field boundary detection. This method stacks multiple network traffic to form an image, designs a field boundary guidance module, and adds self-supervised boundary learning to the loss function, realizing the recognition of field boundaries for fixed-format protocols. We evaluate the proposed approach on 10 widely used protocols. The experimental results demonstrate that EBPFI achieves superior performance in protocol format inference, consistently outperforming all compared methods in terms of F1-score and inference efficiency.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wang, Z., Zhao, S., Qu, Y., Cao, X., Xi, R., Li, L., & Zhu, H. (2026). EBPFI: enhancing binary protocol format inference via field boundary learning. The Computer Journal, 69(11), 1878-1890. https://doi.org/10.1093/comjnl/bxag065

Vancouver

Wang Z, Zhao S, Qu Y, Cao X, Xi R, Li L, et al. EBPFI: enhancing binary protocol format inference via field boundary learning. The Computer Journal. 2026;69(11):1878-1890. doi:10.1093/comjnl/bxag065

BibTeX
@article{Wang2026,
  author = {Wang, Zhen and Zhao, Sen and Qu, Yibo and Cao, Xiurong and Xi, Rongrong and Li, Lun and Zhu, Hongsong},
  title = {EBPFI: enhancing binary protocol format inference via field boundary learning},
  journal = {The Computer Journal},
  year = {2026},
  volume = {69},
  number = {11},
  pages = {1878--1890},
  doi = {10.1093/comjnl/bxag065}
}
Kostenlos starten →