An Explainable AI Framework For Cyber Threat Detection and Risk Assessment in Intelligent ...

Svedbergopen • September 15, 2026

This study aims to develop an explainable artificial intelligence framework for cyber-threat detection and risk assessment in intelligent networks. The framework combines machine-learning classification with SHAP-based interpretation to improve the transparency of automated cybersecurity decisions. The objective was to evaluate and compare Logistic Regression, Random Forest, XGBoost, and Multilayer Perceptron models for distinguishing benign and malicious network traffic, identify the most influential network features using SHAP analysis, and assess detected threats using a model-derived risk score. The analysis was conducted using labeled network-flow data from the CIC-IDS2017 dataset. Among the evaluated approaches, XGBoost demonstrated the strongest overall classification performance. SHAP analysis identified several network-flow characteristics that substantially influenced the model's predictions, providing insight into its decision-making process. Threat-specific analysis further demonstrated variation in detection performance and risk classification across different attack categories, with most categories receiving high model-derived risk levels and selected categories receiving medium risk classifications. The findings demonstrate that integrating machine-learning detection with explainability and risk assessment can provide a more informative approach to intelligent network security. The proposed framework combines predictive capability with feature-level interpretation and threat-oriented risk information, potentially supporting transparent cybersecurity analysis and informed security decision-making.

Endnote/Zotero/Mendeley (RIS)

This work is licensed under a Creative Commons Attribution 4.0 International License .

Publisher : SvedbergOpen Address: 99 Forest Drive Service Road, Pinelands, Cape Town, South Africa 7405 E-mail : [email protected] Website : Design and Powered By SvedbergOpen

The full story

This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.

Advancements in AI Frameworks for Cyber Threat Detection Recent studies have introduced advanced machine learning frameworks aimed at enhancing cybersecurity risk assessment. Article 1 discusses an explainable AI framework utilizing SHAP analysis for improved transparency in threat detection, achieving notable performance with XGBoost on the CIC-IDS2017 dataset. Article 2 presents an optimized machine learning framework that addresses class imbalance and interpretability issues, reporting LightGBM as the top performer on a synthetic dataset mimicking CIC-IDS2017 characteristics. Both frameworks emphasize the importance of feature selection and risk scoring mechanisms to enhance decision-making in cybersecurity. The studies highlight the growing need for effective tools to combat increasingly sophisticated cyber threats. These frameworks aim to provide actionable insights for network security professionals, potentially improving response times and threat mitigation strategies. 2 sources 40

An Explainable AI Framework For Cyber Threat Detection and Risk Assessment in Intelligent ...

The full story

Extracted Entities

Countries (1)

Email Addresses (1)