EUVIMEDEUVIMED entdecken
Crossref

Large language model based hybrid framework for automatic vulnerability detection with explainable AI for cybersecurity enhancement

Nihala Basheer, Shareeful Islam, Mohammed KS Alwaheidi, Haralambos Mouratidis, Spyridon Papastergiou

Integrated Computer-Aided Engineering · 2026-02 · 33 (1) · 38-54

DOI: 10.1177/10692509251368663 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Integrated Computer-Aided Engineering, online erschienen am 19.08.2025. Verfasst von Nihala Basheer und 4 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 53 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Organizations nowadays rely on intensive software systems to support their business operations but vulnerabilities within these systems can cause potential risks for major disruption. AI-based techniques are now widely considered for vulnera-bility identification; however effectiveness heavily relies on the dataset’s size and quality. These techniques often lack contextual information while processing data and pose challenges in resource-constrained environments. AI models are generally black box in nature which creates additional challenges to understand decision making processes. This work proposes a novel hybrid framework using LLM model based on CodeBERT with integration of fine-tuning and Model-Agnostic Meta-Learning for performing effective vulnerability detection. It includes few-shot learning technique for new vulnerability detection tasks while maintaining high performance on known cases. The approach adopts Explainable AI techniques from four dimensions including attention mechanisms, layer-wise analysis, feature contribution, and model confidence scores to explain model decision making. An experiment demonstrates the framework’s effectiveness, show-ing steady decrease in meta-loss from 0.45 to 0.14, accompanied by increase in support accuracy from 85.2% to 92.5%. These findings establish the proposed framework as a robust and interpretable solution for vulnerability detection and management.

Zitieren

APA

Basheer, N., Islam, S., Alwaheidi, M. K., Mouratidis, H., & Papastergiou, S. (2026). Large language model based hybrid framework for automatic vulnerability detection with explainable AI for cybersecurity enhancement. Integrated Computer-Aided Engineering, 33(1), 38-54. https://doi.org/10.1177/10692509251368663

Vancouver

Basheer N, Islam S, Alwaheidi MK, Mouratidis H, Papastergiou S. Large language model based hybrid framework for automatic vulnerability detection with explainable AI for cybersecurity enhancement. Integrated Computer-Aided Engineering. 2026;33(1):38-54. doi:10.1177/10692509251368663

BibTeX
@article{Basheer2026,
  author = {Basheer, Nihala and Islam, Shareeful and Alwaheidi, Mohammed KS and Mouratidis, Haralambos and Papastergiou, Spyridon},
  title = {Large language model based hybrid framework for automatic vulnerability detection with explainable AI for cybersecurity enhancement},
  journal = {Integrated Computer-Aided Engineering},
  year = {2026},
  volume = {33},
  number = {1},
  pages = {38--54},
  doi = {10.1177/10692509251368663}
}
Kostenlos starten →