The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
Are Textual Prompts in Large Language Models Sufficient for Vulnerability Detection?
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.
|
|
|