Efficient Software Vulnerability Detection Using Transformer-based Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Shaik, Sameer, Huang, Zhen, Raicu, Daniela Stan, Furst, Jacob
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910091056250880
author Shaik, Sameer
Huang, Zhen
Raicu, Daniela Stan
Furst, Jacob
author_facet Shaik, Sameer
Huang, Zhen
Raicu, Daniela Stan
Furst, Jacob
contents Detecting software vulnerabilities is critical to ensuring the security and reliability of modern computer systems. Deep neural networks have shown promising results on vulnerability detection, but they lack the capability to capture global contextual information on vulnerable code. To address this limitation, we explore the application of transformers for C/C++ vulnerability detection. We use program slices that encapsulate key syntactic and semantic features of program code, such as API function calls, array usage, pointer manipulations, and arithmetic expressions. By leveraging transformers' capability to capture both local and global contextual information on vulnerable code, our work can identify vulnerabilities accurately. Combined with data balancing and hyperparameter fine-tuning, our work offers a robust and efficient approach to identifying vulnerable code with moderate resource usage and training time.
format Preprint
id arxiv_https___arxiv_org_abs_2604_00112
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Efficient Software Vulnerability Detection Using Transformer-based Models
Shaik, Sameer
Huang, Zhen
Raicu, Daniela Stan
Furst, Jacob
Cryptography and Security
Machine Learning
Software Engineering
Detecting software vulnerabilities is critical to ensuring the security and reliability of modern computer systems. Deep neural networks have shown promising results on vulnerability detection, but they lack the capability to capture global contextual information on vulnerable code. To address this limitation, we explore the application of transformers for C/C++ vulnerability detection. We use program slices that encapsulate key syntactic and semantic features of program code, such as API function calls, array usage, pointer manipulations, and arithmetic expressions. By leveraging transformers' capability to capture both local and global contextual information on vulnerable code, our work can identify vulnerabilities accurately. Combined with data balancing and hyperparameter fine-tuning, our work offers a robust and efficient approach to identifying vulnerable code with moderate resource usage and training time.
title Efficient Software Vulnerability Detection Using Transformer-based Models
topic Cryptography and Security
Machine Learning
Software Engineering
url https://arxiv.org/abs/2604.00112