A large language model-based analysis of vulnerability discovery in windows software

Author First name, Last name, Institution

• Puya Pakshad, College of Computing
• Samson Quaye, College of Computing
• Jamal Al-Karaki, Zayed University, Abu Dhabi CampusFollow
• Marwan Omar, College of Computing
• Maurice E. Dawson, College of Computing

Document Type

Article

Source of Publication

International Journal of Mathematics and Computer in Engineering

Publication Date

6-2-2026

Abstract

Source code security auditing is essential before software release in order to identify programming faults that may lead to vulnerabilities and functional failures. In this paper, we present a structured security assessment of the Windows App SDK by integrating multiple static analysis tools with a context-aware and disagreement-aware Large Language Model (LLM) interpretation layer. Although static analyzers are effective in reporting potential weaknesses, their raw outputs often contain redundant alerts, limited contextual explanation, and inconsistent severity assignments. To address these limitations, the proposed LLM-based interpretation layer normalizes and de-duplicates alerts, filters context-limited or nonactionable warnings, and refines severity prioritization under inter-tool disagreement without introducing new vulnerability discoveries. Experimental results show the security findings before and after LLM-based interpretation. In particular, the proposed framework reduces static-analysis alerts by 62.5%. In addition, disagreement-aware severity refinement eliminates over-prioritized critical findings and improves prioritization by reducing Medium findings from 11 to 7 and Low findings from 42 to 28. These results demonstrate the potential of LLM-based interpretation to reduce noise in static-analysis outputs and improve vulnerability prioritization for practical security assessment.

DOI Link

10.2478/ijmce-2026-0019

ISSN

2956-7068

Publisher

Walter de Gruyter GmbH

Volume

4

Issue

2

First Page

351

Last Page

372

Disciplines

Computer Sciences

Keywords

large language models, Software security, static code analysis, vulnerability discovery, Windows App SDK

Scopus ID

105041052045

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Recommended Citation

Pakshad, Puya; Quaye, Samson; Al-Karaki, Jamal; Omar, Marwan; and Dawson, Maurice E., "A large language model-based analysis of vulnerability discovery in windows software" (2026). All Works. 8262.
https://zuscholars.zu.ac.ae/works/8262

Indexed in Scopus

yes

Open Access

yes

Open Access Type

Hybrid: This publication is openly available in a subscription-based journal/series