EUVIMEDEUVIMED entdecken
Crossref

Payload-Aware Intrusion Detection with CMAE and Large Language Models

Yong Cheol Kim, ChanJae Lee, Young Yoon

ACM Transactions on Privacy and Security · 28.02.2026 · 29 (1) · 1-30

DOI: 10.1145/3769682 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Privacy and Security, online erschienen am 29.11.2025. Verfasst von Yong Cheol Kim und 2 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 90 Literaturangaben. Gefördert von: MSIT, ITRC, IITP.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Intrusion Detection Systems (IDS) play a vital role in network security, yet signature-based methods are limited by high false positive rates (FPR) and inability to detect novel threats. Recent AI-based approaches offer improved adaptability, but most rely on flow-level or statistical features, constraining their ability to analyze sophisticated payload-based attacks. To address these challenges, we present a dual-path IDS framework: Xavier-CMAE, a lightweight model using Hex2Int tokenization and Xavier initialization, achieves 99.9718% accuracy and a 0.0182% FPR without pre-training; and LLM-CMAE, which leverages pre-trained LLM tokenizers for enhanced detection, achieves 99.9696% accuracy and a 0.0194% FPR at higher computational cost. Experimental results on the CIC-IDS2017 dataset reveal a distinct trade-off between efficiency and Contextually Adept and Scalable (CAS) power, indicating that a modular approach may enable both real-time scalability and in-depth threat analysis. This work advances AI-powered intrusion detection by (1) introducing a modular, payload-centric dual-path architecture that combines lightweight and CAS detection for adaptive, layered security; (2) demonstrating that Xavier-CMAE achieves real-time scalability and state-of-the-art accuracy without embedding pre-training; and (3) exploring the effectiveness and future potential of integrating pre-trained LLM tokenizers for nuanced, selective threat analysis and robust IDS design.

Förderung

  • MSIT
  • ITRC
  • IITP
  • NRF
  • Korea government

Zitieren

APA

Kim, Y. C., Lee, C., & Yoon, Y. (2026). Payload-Aware Intrusion Detection with CMAE and Large Language Models. ACM Transactions on Privacy and Security, 29(1), 1-30. https://doi.org/10.1145/3769682

Vancouver

Kim YC, Lee C, Yoon Y. Payload-Aware Intrusion Detection with CMAE and Large Language Models. ACM Transactions on Privacy and Security. 2026;29(1):1-30. doi:10.1145/3769682

BibTeX
@article{Kim2026,
  author = {Kim, Yong Cheol and Lee, ChanJae and Yoon, Young},
  title = {Payload-Aware Intrusion Detection with CMAE and Large Language Models},
  journal = {ACM Transactions on Privacy and Security},
  year = {2026},
  volume = {29},
  number = {1},
  pages = {1--30},
  doi = {10.1145/3769682}
}
Kostenlos starten →