Explainable Security Requirements Classification Through Transformer Models
Open Access
- 3 January 2025
- journal article
- research article
- Published by MDPI AG in Future Internet
- Vol. 17 (1) , 15
Abstract
Security and non-security requirements are two critical issues in software development. Classifying requirements is crucial as it aids in recalling security needs during the early stages of development, ultimately leading to enhanced security in the final software solution. However, it remains a challenging task to classify requirements into security and non-security categories automatically. In this work, we propose a novel method for automatically classifying software requirements using transformer models to address these challenges. In this work, we fine-tuned four pre-trained transformers using four datasets (the original one and the three augmented versions). In addition, we employ few-shot learning techniques by leveraging transfer learning models, explicitly utilizing pre-trained architectures. The study demonstrates that these models can effectively classify security requirements with reasonable accuracy, precision, recall, and F1-score, demonstrating that the fine-tuning and SetFit can help smaller models generalize, making them suitable for enhancing security processes in the Software Development Cycle. Finally, we introduced the explainability of fine-tuned models to elucidate how each model extracts and interprets critical information from input sequences through attention visualization heatmaps.Keywords
Funding Information
- EU DUCA (PE00000014)
- EU CyberSecPro (PE00000014)
- SYNAPSE, PTR 22-24 P2.01 (PE00000014)
- SERICS (PE00000014)
This publication has 23 references indexed in Scilit:
- A Method for AI-generated sentence detection through Large Language ModelsProcedia Computer Science, 2024
- Isolation forest-voting fusion-multioutput: A stroke risk classification method based on the multidimensional output of abnormal sample detectionComputer Methods and Programs in Biomedicine, 2024
- LA-ViT: A Network With Transformers Constrained by Learned-Parameter-Free Attention for Interpretable Grading in a New Laryngeal Histopathology Image DatasetIEEE Journal of Biomedical and Health Informatics, 2024
- MamlFormer: Priori-experience guiding transformer network via manifold adversarial multi-modal learning for laryngeal histopathological gradingInformation Fusion, 2024
- Zero-shot learning for requirements classification: An exploratory studyInformation and Software Technology, 2023
- ASI-DBNet: An Adaptive Sparse Interactive ResNet-Vision Transformer Dual-Branch Network for the Grading of Brain Cancer Histopathological ImagesInterdisciplinary Sciences: Computational Life Sciences, 2022
- Systematic Mapping Study on Security Approaches in Secure Software EngineeringIEEE Access, 2021
- Generalizing from a Few ExamplesACM Computing Surveys, 2020
- Rapid quality assurance with Requirements SmellsJournal of Systems and Software, 2017
- Automating trade-off analysis of security requirementsRequirements Engineering, 2015