# Network Intrusion Forensic Detection System with Explainable Artificial Intelligence and Digital Chain of Custody

DevFeed: [Network Intrusion Forensic Detection System with Explainable Artificial Intelligence and Digital Chain of Custody](<https://devfeed.tech/articles/network-intrusion-forensic-detection-system-with-explainable-artificial-intelligence-and-digital-chain-of-custody-118703.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.06173>)

Author: Jose Luis Vela Alonso, Carmen Pellicer

Published: 2026-11-05T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [ai security](<https://devfeed.tech/topics/ai-security.md>), [Trustworthy AI](<https://devfeed.tech/topics/trustworthy-ai.md>), [ai evaluation](<https://devfeed.tech/topics/ai-evaluation.md>), [AI Research](<https://devfeed.tech/topics/ai-research.md>)

Tags: [aggregation](<https://devfeed.tech/tags/aggregation.md>), [alert](<https://devfeed.tech/tags/alert.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [certification](<https://devfeed.tech/tags/certification.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [detection](<https://devfeed.tech/tags/detection.md>), [explainability](<https://devfeed.tech/tags/explainability.md>), [feature](<https://devfeed.tech/tags/feature.md>), [firewall](<https://devfeed.tech/tags/firewall.md>), [flow](<https://devfeed.tech/tags/flow.md>), [forensic](<https://devfeed.tech/tags/forensic.md>), [formal](<https://devfeed.tech/tags/formal.md>), [inference](<https://devfeed.tech/tags/inference.md>), [intrusion-detection](<https://devfeed.tech/tags/intrusion-detection.md>), [leak](<https://devfeed.tech/tags/leak.md>), [logs](<https://devfeed.tech/tags/logs.md>), [malicious](<https://devfeed.tech/tags/malicious.md>), [model](<https://devfeed.tech/tags/model.md>), [network](<https://devfeed.tech/tags/network.md>), [network-intrusion](<https://devfeed.tech/tags/network-intrusion.md>), [system](<https://devfeed.tech/tags/system.md>)

## AI overview

MODEXRE separates model certification in Laboratory mode from case analysis in Formal mode, which uses a frozen, hash-verified model and a SHA-256 hash-chained custody record. It normalizes Suricata alerts, CEF firewall logs and packet captures through OCSF, and reports per-prediction SHAP explanations. Observed failures prompted corrections: removing a timestamp leak lowered Kitsune F1-macro from 0.984 to 0.662, while causal temporal flow aggregation raised its multiclass score from 0.394 to 0.932. A real packet capture exposed that the pipeline had been training a binary classifier; after correction, 87% of its events were classified Normal and the scanning host Reconnaissance. The four-class certified model scored 0.9538 on CICIDS2017-derived evidence, while the recertified 18-category model scored 0.6214, reflecting the more complex multiclass task.

## Source excerpt

arXiv:2611.06173v1 Announce Type: new Abstract: Deploying an explainable intrusion detection model from a validated laboratory setting into a forensic workflow requires guarantees that benchmarks do not test: that the certified model is the exact artifact applied to a case, that heterogeneous evidence can be classified reliably, and that every step is verifiable. We present MODEXRE, a forensic pipeline that extends a previously validated synthetic-data-trained XGBoost classifier with SHAP explainability (arXiv:2607.00763) into a dual-mode architecture: a Laboratory mode, where models are trained and certified on public and synthetic data, and a Formal mode, where a frozen, hash-verified model performs inference on case evidence under a SHA-256 hash-chained chain of custody. Suricata alerts, CEF firewall logs and packet captures are normalized through OCSF. Four design decisions, each triggered by an observed failure, shaped the architecture: a timestamp leak that inflated Kitsune performance (F1-macro 0.984, 0.662 after correction); a feature-coverage gap that made the 78-feature reference model misclassify a real SSH alert; causal temporal flow aggregation, which raised Kitsune multiclass F1-macro from 0.394 to 0.932; and a certification defect, exposed only by a real packet capture, whereby the pipeline had always trained a binary classifier. After correction, the same capture went from 100% of events flagged as malicious to 87% classified as Normal, with the scanning host identified as Reconnaissance. The default four-class certified model reaches F1-macro = 0.9538 on CICIDS2017-derived evidence; the recertified 18-category model reaches 0.6214, reflecting the real multiclass task. Chain-of-custody verification, model integrity hashing and per-prediction SHAP explanations are reported as measured outcomes.