VulStyle: A Multi-Modal Pre-Training for Code Stylometry-Augmented Vulnerability Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911630904786944 |
|---|---|
| author | Biringa, Chidera Abbas, Ajmal Selvaraj, Vishnu Kul, Gokhan |
| author_facet | Biringa, Chidera Abbas, Ajmal Selvaraj, Vishnu Kul, Gokhan |
| contents | We present VulStyle, a multi-modal software vulnerability detection model that jointly encodes function-level source code, non-terminal Abstract Syntax Tree (AST) structure, and code stylometry (CStyle) features. Prior work in code representation primarily leverages token-level models or full AST trees, often missing stylistic cues indicative of risky programming practices, or incurring high structural overhead. Our approach selects only non-terminal AST nodes, reducing input complexity while preserving semantic hierarchy, and integrates syntactic and lexical CStyle features as auxiliary vulnerability signals.
VulStyle is pre-trained using masked language modeling on 4.9M functions across seven programming languages, and fine-tuned across five benchmark datasets: Devign, BigVul, DiverseVul, REVEAL, and VulDeePecker. VulStyle achieves state-of-the-art performance on BigVul and VulDeePecker, improving F1 by 4-48% over strong transformer baselines, and attains competitive or best-average performance across all benchmarks. We contribute an ablation study isolating the effect of CStyle and AST structure, error case analysis, and a threat model situating the detection task in attacker-realistic scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_26313 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | VulStyle: A Multi-Modal Pre-Training for Code Stylometry-Augmented Vulnerability Detection Biringa, Chidera Abbas, Ajmal Selvaraj, Vishnu Kul, Gokhan Cryptography and Security Machine Learning We present VulStyle, a multi-modal software vulnerability detection model that jointly encodes function-level source code, non-terminal Abstract Syntax Tree (AST) structure, and code stylometry (CStyle) features. Prior work in code representation primarily leverages token-level models or full AST trees, often missing stylistic cues indicative of risky programming practices, or incurring high structural overhead. Our approach selects only non-terminal AST nodes, reducing input complexity while preserving semantic hierarchy, and integrates syntactic and lexical CStyle features as auxiliary vulnerability signals. VulStyle is pre-trained using masked language modeling on 4.9M functions across seven programming languages, and fine-tuned across five benchmark datasets: Devign, BigVul, DiverseVul, REVEAL, and VulDeePecker. VulStyle achieves state-of-the-art performance on BigVul and VulDeePecker, improving F1 by 4-48% over strong transformer baselines, and attains competitive or best-average performance across all benchmarks. We contribute an ablation study isolating the effect of CStyle and AST structure, error case analysis, and a threat model situating the detection task in attacker-realistic scenarios. |
| title | VulStyle: A Multi-Modal Pre-Training for Code Stylometry-Augmented Vulnerability Detection |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2604.26313 |