.png){kind=icon}
.png){kind=icon}
Return
A responsible AI-driven framework for robust and transparent software vulnerability detection
.png){kind=icon}
OA
AI
DOI：10.1016/j.infsof.2026.108126.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Context: Software vulnerability detection (SVD) is increasingly challenged by the scale and complexity of modern software systems. Although deep learning and LLM-based approaches demonstrate strong detection performance, their adoption in security-critical settings is limited by insufficient interpretability, adversarial resilience, and systematic Responsible AI integration. Objective: This paper aims to design and evaluate a Responsible AI-driven framework for SVD that operationalizes fairness, interpretability, security, reliability, and transparency without compromising detection effectiveness. Method: We propose a model-agnostic vulnerability detection framework that incorporates fairness-aware data preprocessing, multi-model evaluation, and structured verification mechanisms. Interpretability is achieved through multi-view explanations combining global and local SHAP, LIME, and attention-based attribution. Explanation consistency is examined using attention-guided token occlusion, while security is evaluated via multiple white-box adversarial attacks on correctly classified test samples. The framework is validated on three public datasets - CWE-119, CWE-399, and DiverseVul - using deep learning and pre-trained LLMs. Results: Experimental results demonstrate competitive detection performance across datasets while providing structured explanation and adversarial evaluation evidence. Interpretability analyses reveal dataset-specific vulnerability cues aligned with domain knowledge, and perturbation studies show consistent confidence shifts under controlled token masking. Adversarial experiments further illustrate stable performance trends under attack conditions. Conclusion: The findings indicate that Responsible AI principles can be systematically operationalized within deep learning and LLM-based SVD pipelines. By integrating fairness, interpretability, security evaluation, reliability assessment, and transparency mechanisms, the proposed framework supports trustworthy and security-aware deployment of AI-driven vulnerability detection systems.
Keywords:
Responsible AI
Software vulnerability detection
Security
Deep learning
Large Language Model (LLMs)
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.3
Papers:
3.7K
Citations:
7.7K
Organization
View more organizations