IRMA-International.org: Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

Are Textual Prompts in Large Language Models Sufficient for Vulnerability Detection?

Are Textual Prompts in Large Language Models Sufficient for Vulnerability Detection?
View Sample PDF
Author(s): Puya Pakshad (Illinois Institute of Technology, USA)and Sajad Aqanasiri (Shahid Beheshti University, Iran)
Copyright: 2025
Pages: 18
Source title: Navigating Law and Policy in STM Enterprises: Ethical Governance, Regulation, and Innovation Strategy
Source Author(s)/Editor(s): Hewa Majeed Zangana (Duhok Polytechnic University, Iraq), Jamal Al-Karaki (Zayed University, UAE)and Marwan Omar (Illinois Institute of Technology, USA)
DOI: 10.4018/979-8-3373-4862-9.ch005

Purchase

View Are Textual Prompts in Large Language Models Sufficient for Vulnerability Detection? on the publisher's website for pricing and purchasing information.

Abstract

Large Language Models (LLMs) have gained traction in domains from software development to cybersecurity, particularly for detecting vulnerabilities in program source code. Their ability to analyze large codebases and identify security weaknesses makes them valuable in software security analysis. However, their effectiveness declines in the absence of intermediate representations such as Abstract Syntax Trees (AST), Control Flow Graphs (CFG), and Data Flow Graphs (DFG), or even tokenized forms of code. In this research study, we assess the performance of LLMs in detecting vulnerabilities directly from raw source code, without structural representations. By designing context-specific prompts, we aim to enhance the model's understanding of code semantics. Our findings show that LLMs can partially identify vulnerabilities from raw code alone, reaching up to 43% accuracy. This indicate both the potential and current limitations of prompt-based LLMs for static vulnerability detection.

Related Content

Siraj Kariyilaparambu Kunjumuhammed. © 2026. 28 pages.
Abel Jacob, Abhinav Kataria, Pankaj Dhaundiyal. © 2026. 28 pages.
Siraj Kariyilaparambu Kunjumuhammed. © 2026. 26 pages.
Antonio Pesqueira, Dora Almeida. © 2026. 28 pages.
Shanmuga Pria, Iman Al Rubaie, Venkata vara Prasad. © 2026. 24 pages.
Devender K, Kafila M, Geetha Manoharan. © 2026. 18 pages.
Terezin Mathew, Roshna Varghese, K Latha. © 2026. 36 pages.
Body Bottom