Intrusion Detection Based on Privacy-Preserving Federated Learning for the Industrial IoT

Ruzafa-Alcazar, Pedro; Fernandez-Saura, Pablo; Marmol-Campos, Enrique; González-Vidal, Aurora; Hernández-Ramos, José L.; Bernal, Jorge; Skarmeta, Antonio F.

doi:10.1109/tii.2021.3126728

Cited by 69 publications

(27 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, So, Güler, and Avestimehr (2020) implements a variant of Krum called multi-Krum, in which the update generated by the aggregator in each round is based on averaging several updates provided by the clients. While collusion attacks are considered, these are related to privacy aspects Ruzafa-Alcázar, Fernández-Saura, Mármol-Campos, González-Vidal, Hernández-Ramos, Bernal-Bernabe, and Skarmeta (2021).…”

Section: Related Workmentioning

confidence: 99%

Evaluating Federated Learning for intrusion detection in Internet of Things: Review and challenges

et al. 2022

Self Cite

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Evaluating Federated Learning for intrusion detection in Internet of Things: Review and challenges

et al. 2022

Self Cite

View full text Add to dashboard Cite

“…In that sense, our approach potentially preserves the privacy of the buildings. Further investigation with privacy-preserving techniques should be done in that sense in order to diminish the security risks associated with data sharing [54]. Some works are already investigating how to incorporate Federated Learning to the smart buildings scenarios in order to keep privacy [55].…”

Section: B Transfer Learning Algorithm For Time Series Predictionmentioning

confidence: 99%

A Transfer Learning Framework for Predictive Energy-Related Scenarios in Smart Buildings

González-Vidal

Mendoza-Bernal

Skarmeta

et al. 2023

IEEE Trans. on Ind. Applicat.

View full text Add to dashboard Cite

Human activities and city routines follow patterns. Transfer learning can help achieve scalable solutions towards the realisation of smart cities accounting for similarities between regions, domains, and activities. In this study, we propose a Transfer Learning-based framework for smart buildings to test this hypothesis in energy-related problems. Our framework has two major components: the network creation and the transferable predictive model. In order to create the network that groups buildings sharing characteristics, we evaluated two strategies: a novel clustering algorithm for mixed data, k-prod, and clustering the image-based representation of time series. Then, a combination of Long Short Term Memory and Convolutional Neural Network was trained on the centroids of the clusters for energy consumption prediction. The Coefficient of Variation of the Root Mean Squared Error (CVRMSE) of the predictions in such clusters vary between 3.85 and 58.85 %. The obtained parameters were transferred to the rest of the buildings for predictive purposes, finding accurate results in buildings with little data. Our framework deals with insufficient training data since parameters from scenarios with more sensors can be received. It also carries out state-of-the-art performance on 3 datasets from different sources having in total 533 rooms/buildings and two energy efficiency domains: consumption prediction reducing the CVRMSE in a 21.6 %, and air conditioning usage prediction moving from a 4.18 % to a 0.28% CVRMSE. Our framework extracts more knowledge from available IoT deployments, so that smartness could be spread between environments at a fewer cost given that less individual effort will be needed.

show abstract

“…Alcazar et al [25] proposed federated learning-based intrusion detection using ensemble approaches for IoT environments. The proposed work includes four processes: data preprocessing, dimensionality reduction, model validation, and intrusion detection.…”

Section: Literature Surveymentioning

confidence: 99%

Twin chain: A Blockchain based Federated Learning Intrusion Detection System usingOptimized Backpropagation based Neural Network for Edge Assisted IoT Networks

Narayanan

Paul

2023

Preprint

View full text Add to dashboard Cite

Ensuring security and privacy in IoT environments is a critical concern due to the prevalence of intrusions. Federated learning (FL) has emerged as a prominent technology for intrusion detection without compromising data privacy. This study proposes a novel model called BlockFL-IDS (Blockchain-based Federated Learning for Intrusion Detection System) that combines blockchain and deep learning approaches for effective intrusion detection. The BlockFL-IDS model consists of three key processes: efficient client selection, secure channel selection, and federated learning-based IDS. To streamline the complexity of federated learning, we employ Auction game theory to select efficient clients based on metrics such as trust, energy, bandwidth, and network conditions. Furthermore, we employ the Base Criterion Method (BCM), a multicriteria decision-making algorithm, for secure channel selection. BCM evaluates multiple criteria, including noise, path loss, channel quality, stability, trust, and fading, resulting in improved accuracy and reduced data loss in intrusion detection. For federated learning, we utilize the Optimized Back Propagation-based Deep Belief Network (OB-DBN), enabling the generation of both local and global models. The edge server generates local models, extracting packet-based features from client data for intrusion detection. Cloud servers aggregate these local models to create global models stored in a circular-based regression tree structure to enhance scalability and reduce retrieval time. The proposed OB-DBN algorithm calculates backpropagation error, facilitating loss reduction and weight updates. To evaluate the performance of the BlockFL-IDS model, we implement it using the NS-3.26 network simulator and assess its effectiveness using various performance metrics. Through our research, we aim to address security and privacy concerns in IoT environments, providing an innovative solution that enhances intrusion detection while preserving data privacy.

show abstract

Intrusion Detection Based on Privacy-Preserving Federated Learning for the Industrial IoT

Cited by 69 publications

References 26 publications

Evaluating Federated Learning for intrusion detection in Internet of Things: Review and challenges

Evaluating Federated Learning for intrusion detection in Internet of Things: Review and challenges

A Transfer Learning Framework for Predictive Energy-Related Scenarios in Smart Buildings

Twin chain: A Blockchain based Federated Learning Intrusion Detection System usingOptimized Backpropagation based Neural Network for Edge Assisted IoT Networks

Contact Info

Product

Resources

About