[Paper] Early Comparative Evaluation of Transformer Models for Multilingual Software Vulnerability Detection

Source: arXiv - 2606.10925v1

Overview

Software vulnerability detection is increasingly important as modern applications combine multiple programming languages. This paper presents an early comparative evaluation of BERT, RoBERTa, and CodeBERT for binary vulnerability detection across HTML, Python, JavaScript, and PHP using the CVEFixes dataset and language-wise three-fold stratified cross-validation. The results show clear performance differences across languages, indicating that multilingual vulnerability detection requires more language-aware and robust transformer-based modelling strategies.

Key Contributions

This paper presents research in the following areas:

• cs.SE

Methodology

Please refer to the full paper for detailed methodology.

Practical Implications

This research contributes to the advancement of cs.SE.

Authors

• Fiza Naseer
• Javad Khan
• Muhammad Yaqoob
• Alexios Mylonas

Paper Information

• arXiv ID: 2606.10925v1
• Categories: cs.SE
• Published: June 9, 2026
• PDF: Download PDF