Federated Learning for Internet of Things: A Federated Learning Framework for On-device Anomaly Data Detection

Zhang, Tuo; He, Chaoyang; Ma, Tianhao; Gao, Lei; Ma, Mark; Avestimehr, Salman

doi:10.48550/arxiv.2106.07976

Cited by 5 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FL has enabled the devices to share only the weights learned with the global server of the federated model. The FL-based security solution in [16] improves the attack detection accuracy by effectively designing the learning model with a local adaptive optimizer, such as the Adam optimizer and a cross-round learning rate scheduler.…”

Section: Federated Learning-based Iot Security Schemesmentioning

confidence: 99%

See 1 more Smart Citation

Optimized Federated Learning with Ensemble of Sequential Models for Detecting RPL Routing Attacks for AMI Networks

Sharma

Sakthivel²,

Alnajjar

2023

Preprint

View full text Add to dashboard Cite

With the rapid expansion of smart applications and services, the Internet of Things (IoT) plays a vital role in enabling changes in the usage of information and communication technology. Advanced Metering Infrastructure (AMI) is the key component of the smart grid which often meets privacy and security threats from the routing layer. The Routing Protocol for Low-Power and Lossy Networks (RPL) is the prominent routing protocol for AMI networks, and securing the RPL is the cornerstone of all security controls in the AMI for successful deployment. Recently, IoT security systems have increasingly adopted privacy-preserving Federated Learning (FL) that trains a local data model across multiple decentralized edge devices and takes global decisions without the need for global data sharing. Relying on a single learning model significantly degrades the FL performance due to the frequent transmission of weights and training on heterogeneous IoT networks. This paper proposes an Optimized FL model for Securing RPL (OFL-SRPL) over AMI devices. By reducing the size of the data transferred from the multiple local models to the server, the OFL-SRPL adopted the Particle Swam Optimization (PSO) algorithm to select the best local model from the Home Area Network (HAN) gateway and build the global model. The proposed OFL-SRPL applies an ensemble of sequential classifiers with its appropriate loss function to improve the decision-making quality and reduce the FL communication burden. Instead of transferring all the local model weights to the global model, the OFL-SRPL iteratively selects the best ensemble model with sequential classifies and only sends the weight of the best model to build the global model. The sequential classifier design improves the ownership weight and handles class imbalance issues. After taking an optimized global model decision, the devices execute ensemble classifiers successfully with appropriate learning parameters. Thus, the proposed OFL-SRPL achieves 10.6% higher detection accuracy than a centralized setup of the Long Short-Term Memory (LSTM) model without incurring multiple communication rounds like traditional FL.

show abstract

Section: Federated Learning-based Iot Security Schemesmentioning

confidence: 99%

“…The work in [16] is the first attempt to explain various use cases to issues and scopes for future enhancements. The FLGUARD, a poisoning defense framework, is developed in [17], and it provides data security and privacy without losing the benign performance of the aggregated model.…”

Section: Federated Learning-based Iot Security Schemesmentioning

confidence: 99%

Optimized Federated Learning with Ensemble of Sequential Models for Detecting RPL Routing Attacks for AMI Networks

Sharma

Sakthivel²,

Alnajjar

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The average available bandwidth between the device and server is 75Mbps. The experiments are carried out in a real-world environment with 5 IoT devices, which is similar to testbeds employed in peer reviewed research on FL [8], [9], [42].…”

Section: B Rl Optimization For Heterogeneitymentioning

confidence: 99%

FedAdapt: Adaptive Offloading for IoT Devices in Federated Learning

Ullah

Harvey

et al. 2022

IEEE Internet Things J.

View full text Add to dashboard Cite

“…Zhang et al 29 created a system for actual FL assessment on IoT devices and a platform for on-device anomaly data detection named FedIoT and proposed the Fed Detect algorithm. In addition, the presented Fed Detect learning system enhances performance by incorporating an adaptive threshold optimization and a cross-round learning rate scheduler.…”

Section: Securitymentioning

confidence: 99%

Federated learning‐based IoT: A systematic literature review

Hosseinzadeh

Hemmati

Rahmani

2022

Int J Communication

View full text Add to dashboard Cite

Summary The Internet of Things (IoT) has a significant impact on our daily lives as applications, services, devices, and industries become more intelligent. Artificial intelligence (AI) is expected to significantly influence machine learning training on IoT devices without data sharing. Federated learning (FL) is a distributed machine learning method used in many IoT smart devices; however, FL ensures IoT security and privacy. The systematic literature review (SLR) method is used in this paper to review recently published articles in the FL‐based IoT domain. We analyzed 39 papers that were published between 2018 and March 2022. According to the evaluation factors, the accuracy factor has a high percentage in the FL‐based IoT domain by 29%, and the epoch has 23%, the time has 18%, the energy consumption has 9%, the delay has 9%, the communication overhead has 6%, and the privacy has 6%. Finally, we discuss future research challenges and open issues in the context of FL‐based IoT.

show abstract

Federated Learning for Internet of Things: A Federated Learning Framework for On-device Anomaly Data Detection

Cited by 5 publications

References 21 publications

Optimized Federated Learning with Ensemble of Sequential Models for Detecting RPL Routing Attacks for AMI Networks

Optimized Federated Learning with Ensemble of Sequential Models for Detecting RPL Routing Attacks for AMI Networks

FedAdapt: Adaptive Offloading for IoT Devices in Federated Learning

Federated learning‐based IoT: A systematic literature review

Contact Info

Product

Resources

About