EUVIMEDEUVIMED entdecken
StudienprotokollOpen Access · CC BY 4.0

LLMSGen: Generating Diverse Seeds for Multimedia Protocol Fuzzing Leveraging Large Language Models

Chunyang Wan, Yaxin Zhao, Wanli Wu, Kailong Zhu

Electronics · 10.06.2026 · 15 (12) · 2569

DOI: 10.3390/electronics15122569 ↗

Kurz gefasst

Studienprotokoll in der Zeitschrift Electronics, online erschienen am 10.06.2026. Verfasst von Chunyang Wan und 3 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multimedia protocol implementations are susceptible to security vulnerabilities, yet the existing fuzzing methods fail to generate seed corpora covering all supported resource types due to the resource type sensitivity characteristic, resulting in limited code coverage. We propose LLMSGen, a method leveraging Large Language Models (LLMs) to generate diverse seeds for multimedia protocol fuzzing. Through prompt chaining, LLMs analyze the source code of the target program to identify supported resource types and extract URI construction rules. Diverse request seeds are then generated by replacing URI fields in captured traffic, and the corresponding resource files are placed in the server’s working directory to ensure valid responses during fuzzing. Evaluated on three RTSP-based open-source programs (Live555, RTSPServer, Gstreamer), LLMSGen increased resource type coverage by an average of approximately 98.4% and improved code line coverage by approximately 36.8% compared to AFLNet’s original seed corpus.

Zitieren

APA

Wan, C., Zhao, Y., Wu, W., & Zhu, K. (2026). LLMSGen: Generating Diverse Seeds for Multimedia Protocol Fuzzing Leveraging Large Language Models. Electronics, 15(12), 2569. https://doi.org/10.3390/electronics15122569

Vancouver

Wan C, Zhao Y, Wu W, Zhu K. LLMSGen: Generating Diverse Seeds for Multimedia Protocol Fuzzing Leveraging Large Language Models. Electronics. 2026;15(12):2569. doi:10.3390/electronics15122569

BibTeX
@article{Wan2026,
  author = {Wan, Chunyang and Zhao, Yaxin and Wu, Wanli and Zhu, Kailong},
  title = {LLMSGen: Generating Diverse Seeds for Multimedia Protocol Fuzzing Leveraging Large Language Models},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {12},
  pages = {2569},
  doi = {10.3390/electronics15122569}
}
Kostenlos starten →