Blockchain-Backed ML-Based Zero-Trust Honeypot for Forensic-Ready Cyber-Physical System Security in Industry X
Journal of Computational Science and Applications · 11.12.2025 · 2 (2) · 1-10
DOI: 10.51846/jcsa.v2i2.4636 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computational Science and Applications, online erschienen am 11.12.2025. Verfasst von Mohammad Sayduzzaman und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Cyber-Physical Systems (CPS) in Industry X face evolving threats that outpace perimeter and signature defenses. Cyber-Physical Systems (CPS) in Industry X have progressed from perimeter/signature IDS to (i) deception honeypots, (ii) ML-based IDS, and (iii) blockchain logging; yet these strands remain siloed, yielding gaps in forensic readiness and tamper-proof evidence. We propose a Blockchain-Backed, ML-based Zero-Trust Honeypot that unifies least-privilege control, physics-aware deception, adaptive detection, and immutable chain-of-custody, aligned with IEC 62443, NIST SP 800-207/800-82, and ISO/IEC 27001. Our chronological evaluation mirrors the field’s trajectory: (a) perimeter IDS, (b) Zero-Trust only, (c) Zero-Trust+ML, and (d) full integration. Using published benchmarks as targets, ML-IDS reports ∼ 98.6% accuracy (macro-F1 ∼ 0.972) on SWaT and ∼ 98.9% accuracy (macro-F1 ∼ 0.977) on ToN-IoT; large ICS honeypot deployments have logged > 80,000 interactions across 120 nodes in 22 countries; mature Zero-Trustprograms show ∼ 40–50% faster containment; and tuned permissioned-ledger anchoring can bound throughput overhead to ≤ 10–15% via hash-only commits and block/endorsement tuning. Accordingly, we pre-register targets of ≥ 98% macro-F1, ≥ 40% reduction in MTTD/MTTR versus perimeter baselines, and ≤ 15% throughput overhead, then assess TPR/FPR, macro-F1, evidence-integrity verifications, and ledger latency on physics-aware CPS testbeds. The results close long-standing gaps between real-time defense and legally defensible, immutable forensics, advancing trustworthy, human-centric CPS security for Industry X.
Zitieren
APA
Sayduzzaman, M., & Nawab, M. H. (2025). Blockchain-Backed ML-Based Zero-Trust Honeypot for Forensic-Ready Cyber-Physical System Security in Industry X. Journal of Computational Science and Applications, 2(2), 1-10. https://doi.org/10.51846/jcsa.v2i2.4636
Vancouver
Sayduzzaman M, Nawab MH. Blockchain-Backed ML-Based Zero-Trust Honeypot for Forensic-Ready Cyber-Physical System Security in Industry X. Journal of Computational Science and Applications. 2025;2(2):1-10. doi:10.51846/jcsa.v2i2.4636
BibTeX
@article{Sayduzzaman2025,
author = {Sayduzzaman, Mohammad and Nawab, Md Hassan},
title = {Blockchain-Backed ML-Based Zero-Trust Honeypot for Forensic-Ready Cyber-Physical System Security in Industry X},
journal = {Journal of Computational Science and Applications},
year = {2025},
volume = {2},
number = {2},
pages = {1--10},
doi = {10.51846/jcsa.v2i2.4636}
}
EUVIMED