Explainable AI for Forensic Analysis: A Comparative Study of SHAP and LIME in Intrusion Detection Models

The lack of interpretability in AI-based intrusion detection systems poses a critical barrier to their adoption in forensic cybersecurity, which demands high levels of reliability and verifiable evidence. To address this challenge, the integration of explainable artificial intelligence (XAI) into fo...

Full description

Saved in:
Bibliographic Details
Main Authors: Pamela Hermosilla, Sebastián Berríos, Héctor Allende-Cid
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/13/7329
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849429105401921536
author Pamela Hermosilla
Sebastián Berríos
Héctor Allende-Cid
author_facet Pamela Hermosilla
Sebastián Berríos
Héctor Allende-Cid
author_sort Pamela Hermosilla
collection DOAJ
description The lack of interpretability in AI-based intrusion detection systems poses a critical barrier to their adoption in forensic cybersecurity, which demands high levels of reliability and verifiable evidence. To address this challenge, the integration of explainable artificial intelligence (XAI) into forensic cybersecurity offers a powerful approach to enhancing transparency, trust, and legal defensibility in network intrusion detection. This study presents a comparative analysis of SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) applied to Extreme Gradient Boosting (XGBoost) and Attentive Interpretable Tabular Learning (TabNet), using the UNSW-NB15 dataset. XGBoost achieved 97.8% validation accuracy and outperformed TabNet in explanation stability and global coherence. In addition to classification performance, we evaluate the fidelity, consistency, and forensic relevance of the explanations. The results confirm the complementary strengths of SHAP and LIME, supporting their combined use in building transparent, auditable, and trustworthy AI systems in digital forensic applications.
format Article
id doaj-art-e3847b087daf4333a3928bba49d92472
institution Kabale University
issn 2076-3417
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-e3847b087daf4333a3928bba49d924722025-08-20T03:28:28ZengMDPI AGApplied Sciences2076-34172025-06-011513732910.3390/app15137329Explainable AI for Forensic Analysis: A Comparative Study of SHAP and LIME in Intrusion Detection ModelsPamela Hermosilla0Sebastián Berríos1Héctor Allende-Cid2Escuela de Ingeniería Informática, Pontificia Universidad Católica de Valparaíso, Valparaíso 2362807, ChileEscuela de Ingeniería Informática, Pontificia Universidad Católica de Valparaíso, Valparaíso 2362807, ChileEscuela de Ingeniería Informática, Pontificia Universidad Católica de Valparaíso, Valparaíso 2362807, ChileThe lack of interpretability in AI-based intrusion detection systems poses a critical barrier to their adoption in forensic cybersecurity, which demands high levels of reliability and verifiable evidence. To address this challenge, the integration of explainable artificial intelligence (XAI) into forensic cybersecurity offers a powerful approach to enhancing transparency, trust, and legal defensibility in network intrusion detection. This study presents a comparative analysis of SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) applied to Extreme Gradient Boosting (XGBoost) and Attentive Interpretable Tabular Learning (TabNet), using the UNSW-NB15 dataset. XGBoost achieved 97.8% validation accuracy and outperformed TabNet in explanation stability and global coherence. In addition to classification performance, we evaluate the fidelity, consistency, and forensic relevance of the explanations. The results confirm the complementary strengths of SHAP and LIME, supporting their combined use in building transparent, auditable, and trustworthy AI systems in digital forensic applications.https://www.mdpi.com/2076-3417/15/13/7329explainable artificial intelligence (XAI)intrusion detection system (IDS)digital forensicsSHAPLIMEinterpretability evaluation
spellingShingle Pamela Hermosilla
Sebastián Berríos
Héctor Allende-Cid
Explainable AI for Forensic Analysis: A Comparative Study of SHAP and LIME in Intrusion Detection Models
Applied Sciences
explainable artificial intelligence (XAI)
intrusion detection system (IDS)
digital forensics
SHAP
LIME
interpretability evaluation
title Explainable AI for Forensic Analysis: A Comparative Study of SHAP and LIME in Intrusion Detection Models
title_full Explainable AI for Forensic Analysis: A Comparative Study of SHAP and LIME in Intrusion Detection Models
title_fullStr Explainable AI for Forensic Analysis: A Comparative Study of SHAP and LIME in Intrusion Detection Models
title_full_unstemmed Explainable AI for Forensic Analysis: A Comparative Study of SHAP and LIME in Intrusion Detection Models
title_short Explainable AI for Forensic Analysis: A Comparative Study of SHAP and LIME in Intrusion Detection Models
title_sort explainable ai for forensic analysis a comparative study of shap and lime in intrusion detection models
topic explainable artificial intelligence (XAI)
intrusion detection system (IDS)
digital forensics
SHAP
LIME
interpretability evaluation
url https://www.mdpi.com/2076-3417/15/13/7329
work_keys_str_mv AT pamelahermosilla explainableaiforforensicanalysisacomparativestudyofshapandlimeinintrusiondetectionmodels
AT sebastianberrios explainableaiforforensicanalysisacomparativestudyofshapandlimeinintrusiondetectionmodels
AT hectorallendecid explainableaiforforensicanalysisacomparativestudyofshapandlimeinintrusiondetectionmodels