Resource and Heterogeneity-aware Clients Eligibility Protocol in Federated Learning

Asad, Muhammad; Otoum, Safa; Shaukat, Saima

doi:10.1109/globecom48099.2022.10000884

Cited by 5 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even though raw data is not shared, adversaries can analyze the transmitted model updates to infer sensitive information about the participants' data. For instance, property inference attacks aim to deduce the presence of certain features in the data, while membership inference attacks attempt to determine whether specific data points were included in the training set [12]. These vulnerabilities highlight the need for robust privacy-preserving mechanisms in FL.…”

Section: Related Workmentioning

confidence: 99%

“…• TSA: TSA provides a mechanism for secure and verifiable participant authentication without revealing any sensitive information [8]. By using threshold signatures, TSA ensures that only authenticated participants can contribute to the model training process.…”

Section: Limitations Of Existing Approachesmentioning

confidence: 99%

“…In this section, we evaluate the performance of the proposed BPPFL framework in terms of computation overhead, communication overhead, and privacy analysis. We compare the performance of BPPFL with three existing schemes: TSA [8], Federated Optimization (FedOpt) [26], and Privacy-Preserving Deep Learning (PPDL) [27].…”

Section: Performance Evaluationmentioning

confidence: 99%

“…1. TSA: TSA ensures secure and verifiable participant authentication [8]. By using threshold signatures, the identity of each participant is authenticated without revealing any sensitive information.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

BPPFL: A Blockchain-Based Framework for Privacy-Preserving Federated Learning

Asad,

Otoum

2024

Preprint

View full text Add to dashboard Cite

Federated Learning (FL) offers a collaborative approach to training machine learning models while preserving data privacy. However, FL faces significant privacy and security challenges, such as identity disclosure and model inference attacks. To this end, we propose a novel Blockchain-Based Framework for Privacy-Preserving Federated Learning (BPPFL), which integrates threshold signature authentication and threshold Paillier encryption with blockchain technology. The BPPFL framework secures participant authentication and protects against internal and external threats, while the blockchain provides an immutable ledger for recording transactions and model updates, ensuring transparency and security. Experimental results show that our framework significantly reduces computation and communication overhead compared to existing methods while maintaining high model accuracy and robust privacy guarantees. Our framework enhances the security and trustworthiness of FL applications, making it suitable for domains like healthcare, finance, and the IoT.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Limitations Of Existing Approachesmentioning

confidence: 99%

Section: Performance Evaluationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

BPPFL: A Blockchain-Based Framework for Privacy-Preserving Federated Learning

Asad,

Otoum

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…One way to select edge devices is based on their processing power. Devices with more processing power can handle more complex machine learning models and computations [64]. However, devices with more processing power also tend to consume more energy, which can limit their battery life.…”

Section: Device Selectionmentioning

confidence: 99%

Limitations and Future Aspects of Communication Costs in Federated Learning: A Survey

Asad,

Shaukat,

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

This paper explores the potential for communication-efficient federated learning (FL) in modern distributed systems. FL is an emerging distributed machine learning technique that allows for the distributed training of a single machine learning model across multiple geographically distributed clients. This paper surveys the various approaches to communication-efficient FL, including model updates, compression techniques, resource management for the edge and cloud, and client selection. We also review the various optimization techniques associated with communication-efficient FL, such as compression schemes and structured updates. Finally, we highlight the current research challenges and discuss the potential future directions for communication-efficient FL.

show abstract

Federated learning for efficient spectrum allocation in open RAN

Asad,

Otoum

2024

Cluster Comput

View full text Add to dashboard Cite

Resource and Heterogeneity-aware Clients Eligibility Protocol in Federated Learning

Cited by 5 publications

References 13 publications

BPPFL: A Blockchain-Based Framework for Privacy-Preserving Federated Learning

BPPFL: A Blockchain-Based Framework for Privacy-Preserving Federated Learning

Limitations and Future Aspects of Communication Costs in Federated Learning: A Survey

Federated learning for efficient spectrum allocation in open RAN

Contact Info

Product

Resources

About