Work

GreenBERT: A lightweight green transformer for automated prediction of software vulnerability scores

Year: 2025

Type: article

Abstract: Timely assessment of software vulnerabilities is critical for effective patch prioritization, yet manual Common Vulnerability Scoring System (CVSS) scoring remains slow and resource-intensive. While transformer-based models such as BERT have advanced automated scoring, their substantial computational demands conflict with sustainable, green computing objectives. This paper introduces GreenBERT , a tailored ensemble of lightweight student Transformers, each specialized on individual CVSS metrics through a targeted multi-head knowledge distillation framework. By jointly optimizing alignment with ground-truth labels and softened outputs from a fine-tuned BERT teacher, GreenBERT efficiently captures complex vulnerability patterns while significantly reducing computational overhead. Extensive experiments on the National Vulnerability Database (NVD) and a more challenging COMBINED dataset demonstrate that GreenBERT achieves an average F1-score improvement exceeding 6% over the BERT baseline, while simultaneously reducing inference time by approximately 80% and cutting energy usage and CO 2 emissions by about 70%. These results position GreenBERT as a robust, scalable, and environmentally conscious solution for high-performance vulnerability scoring, effectively reconciling the traditionally conflicting goals of predictive accuracy and sustainable AI.

Source: Array

DOI: 10.1016/j.array.2025.100536

Authors: Seyedeh Leili Mirtaheri, Ali Kafi Tafti, Hamid Heidari Soureshjani, Andrea Pugliese

Institutions: University of Calabria, Kharazmi University

Language: English

Topic: Web Application Security Vulnerabilities

Subfield: Information Systems

Field: Computer Science

Domain: Physical Sciences

SDG: Industry, innovation and infrastructure

Open Access status: gold

Estimated APC paid: $1,680