Salvato in:
Dettagli Bibliografici
Autori principali: Ofeidis, Iason, Papadis, Nikos, Bhatia, Randeep, Tassiulas, Leandros, Lakshman, TV
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2605.06571
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914539926192128
author Ofeidis, Iason
Papadis, Nikos
Bhatia, Randeep
Tassiulas, Leandros
Lakshman, TV
author_facet Ofeidis, Iason
Papadis, Nikos
Bhatia, Randeep
Tassiulas, Leandros
Lakshman, TV
contents The rapid expansion of the Internet of Things (IoT) and Industrial IoT (IIoT) has created a massive, heterogeneous attack surface that challenges traditional network security mechanisms. While Federated Learning (FL) offers a privacy-preserving alternative to centralized Intrusion Detection Systems (IDS), standard approaches struggle to generalize across diverse device behaviors and typically fail to utilize the vast amounts of unlabeled data present in realistic edge environments. To bridge these gaps, we propose CLAD, a holistic framework that seamlessly incorporates Clustered Federated Learning (CFL) with a novel Dual-Mode Micro-Architecture ($\text{DM}^2\text{A}$). This unified approach simultaneously tackles the two primary bottlenecks of IoT security: device heterogeneity and label scarcity. The $\text{DM}^2\text{A}$ component features a shared encoder followed by two branches, enabling joint unsupervised anomaly detection and supervised attack classification; this allows the framework to harvest intelligence from both labeled and unlabeled clients. Concurrently, the clustering component dynamically groups devices with congruent traffic patterns, preventing global model divergence. By carefully combining these elements, CLAD ensures that no data is discarded and distinct operational patterns are preserved. Extensive evaluations demonstrate that this integrated approach significantly outperforms state-of-the-art baselines, achieving a 30% relative improvement in detection performance in scenarios with 80% unlabeled clients, with only half the communication cost.
format Preprint
id arxiv_https___arxiv_org_abs_2605_06571
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CLAD: A Clustered Label-Agnostic Federated Learning Framework for Joint Anomaly Detection and Attack Classification
Ofeidis, Iason
Papadis, Nikos
Bhatia, Randeep
Tassiulas, Leandros
Lakshman, TV
Machine Learning
Cryptography and Security
Distributed, Parallel, and Cluster Computing
Networking and Internet Architecture
The rapid expansion of the Internet of Things (IoT) and Industrial IoT (IIoT) has created a massive, heterogeneous attack surface that challenges traditional network security mechanisms. While Federated Learning (FL) offers a privacy-preserving alternative to centralized Intrusion Detection Systems (IDS), standard approaches struggle to generalize across diverse device behaviors and typically fail to utilize the vast amounts of unlabeled data present in realistic edge environments. To bridge these gaps, we propose CLAD, a holistic framework that seamlessly incorporates Clustered Federated Learning (CFL) with a novel Dual-Mode Micro-Architecture ($\text{DM}^2\text{A}$). This unified approach simultaneously tackles the two primary bottlenecks of IoT security: device heterogeneity and label scarcity. The $\text{DM}^2\text{A}$ component features a shared encoder followed by two branches, enabling joint unsupervised anomaly detection and supervised attack classification; this allows the framework to harvest intelligence from both labeled and unlabeled clients. Concurrently, the clustering component dynamically groups devices with congruent traffic patterns, preventing global model divergence. By carefully combining these elements, CLAD ensures that no data is discarded and distinct operational patterns are preserved. Extensive evaluations demonstrate that this integrated approach significantly outperforms state-of-the-art baselines, achieving a 30% relative improvement in detection performance in scenarios with 80% unlabeled clients, with only half the communication cost.
title CLAD: A Clustered Label-Agnostic Federated Learning Framework for Joint Anomaly Detection and Attack Classification
topic Machine Learning
Cryptography and Security
Distributed, Parallel, and Cluster Computing
Networking and Internet Architecture
url https://arxiv.org/abs/2605.06571