PenTiDef: Decentralized Federated Intrusion Detection System with Differential Privacy and Latent-Space Defense via Blockchain Coordination in IIoT

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Duy, Phan The, Khoa, Nghi Hoang, Quan, Nguyen Tran Anh, Tien, Luong Ha, Son, Ngo Duc Hoang, Pham, Van-Hau
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913151646171136
author Duy, Phan The
Khoa, Nghi Hoang
Quan, Nguyen Tran Anh
Tien, Luong Ha
Son, Ngo Duc Hoang
Pham, Van-Hau
author_facet Duy, Phan The
Khoa, Nghi Hoang
Quan, Nguyen Tran Anh
Tien, Luong Ha
Son, Ngo Duc Hoang
Pham, Van-Hau
contents This paper proposes PenTiDef, a fully decentralized, privacy-preserving, and poisoning-resilient framework for decentralized federated IDS (DFL-IDS). PenTiDef synergistically integrates three key components: (i) client-side Distributed Differential Privacy (DDP) with stochastic Gaussian noise to protect gradient leakage, (ii) a lightweight latent-space defense module that extracts and compresses penultimate-layer representations (PLRs) into stable Latent Semantic Representations (LSRs) via AutoEncoder, followed by Centered Kernel Alignment (CKA) and K-Means clustering for robust malicious update detection without auxiliary datasets, and (iii) a permissioned blockchain layer with smart contracts that orchestrates on-chain validation, secure FedAvg aggregation, and immutable auditability, eliminating any central server. Extensive experiments on CIC-IDS2018 and Edge-IIoTSet under both IID and realistic non-IID settings, with adversary ratios up to 40\%, demonstrate that PenTiDef consistently outperforms state-of-the-art baselines (FLARE and FedCC) in detection accuracy and F1-score while maintaining lower training overhead. By jointly addressing privacy, robustness, and decentralization in a unified secure aggregation protocol, PenTiDef provides a practical and scalable solution for trustworthy collaborative intrusion detection in heterogeneous, adversarial IIoT environments.
format Preprint
id arxiv_https___arxiv_org_abs_2602_17973
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PenTiDef: Decentralized Federated Intrusion Detection System with Differential Privacy and Latent-Space Defense via Blockchain Coordination in IIoT
Duy, Phan The
Khoa, Nghi Hoang
Quan, Nguyen Tran Anh
Tien, Luong Ha
Son, Ngo Duc Hoang
Pham, Van-Hau
Cryptography and Security
Artificial Intelligence
This paper proposes PenTiDef, a fully decentralized, privacy-preserving, and poisoning-resilient framework for decentralized federated IDS (DFL-IDS). PenTiDef synergistically integrates three key components: (i) client-side Distributed Differential Privacy (DDP) with stochastic Gaussian noise to protect gradient leakage, (ii) a lightweight latent-space defense module that extracts and compresses penultimate-layer representations (PLRs) into stable Latent Semantic Representations (LSRs) via AutoEncoder, followed by Centered Kernel Alignment (CKA) and K-Means clustering for robust malicious update detection without auxiliary datasets, and (iii) a permissioned blockchain layer with smart contracts that orchestrates on-chain validation, secure FedAvg aggregation, and immutable auditability, eliminating any central server. Extensive experiments on CIC-IDS2018 and Edge-IIoTSet under both IID and realistic non-IID settings, with adversary ratios up to 40\%, demonstrate that PenTiDef consistently outperforms state-of-the-art baselines (FLARE and FedCC) in detection accuracy and F1-score while maintaining lower training overhead. By jointly addressing privacy, robustness, and decentralization in a unified secure aggregation protocol, PenTiDef provides a practical and scalable solution for trustworthy collaborative intrusion detection in heterogeneous, adversarial IIoT environments.
title PenTiDef: Decentralized Federated Intrusion Detection System with Differential Privacy and Latent-Space Defense via Blockchain Coordination in IIoT
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2602.17973