Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

SHAP-RM : An XAI framework for evaluating machine learning reliability

Wang, Xueyi, Li, Shancang and Burnap, Peter ORCID: https://orcid.org/0000-0003-0396-633X 2025. SHAP-RM : An XAI framework for evaluating machine learning reliability. Presented at: The 28th International Symposium on Research in Attacks, Intrusions and Defenses (RAID 2025), Gold Coast, Australia, 19-22 October, 2025.
Item availability restricted.

[thumbnail of Poster] PDF (Poster) - Other
Restricted to Repository staff only until 31 December 2026 due to copyright restrictions.

Download (325kB)

Abstract

This research presents a novel framework, SHAP-RM, for assessing the reliability and trustworthiness of machine learning (ML) models in cyber security applications using explainable artificial intelligence (XAI). By applying SHAP (SHapley Additive exPlanations) to XGBoost regression and classification tasks trained on the live PV generation dataset and the UNSW-NB15 dataset, we examine the interpretability and robustness of model decisions. Integrating XAI enhances transparency, offering actionable insights for refining and securing ML-driven defense systems.

Item Type: Conference or Workshop Item (Poster)
Status: In Press
Schools: Schools > Computer Science & Informatics
Date of First Compliant Deposit: 9 August 2025
Date of Acceptance: 29 July 2025
Last Modified: 12 Aug 2025 10:46
URI: https://orca.cardiff.ac.uk/id/eprint/180317

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics