Federated Learning With Blockchain for Autonomous Vehicles: Analysis and Design Challenges

  title={Federated Learning With Blockchain for Autonomous Vehicles: Analysis and Design Challenges},
  author={Shiva Raj Pokhrel and Jinho Choi},
  journal={IEEE Transactions on Communications},
We propose an autonomous blockchain-based federated learning (BFL) design for privacy-aware and efficient vehicular communication networking, where local on-vehicle machine learning (oVML) model updates are exchanged and verified in a distributed fashion. BFL enables oVML without any centralized training data or coordination by utilizing the consensus mechanism of the blockchain. Relying on a renewal reward approach, we develop a mathematical framework that features the controllable network and… 

Figures from this paper

A Fast Blockchain-Based Federated Learning Framework With Compressed Communications

This work is among the first to propose a fast blockchain-based communication-efficient federated learning framework by compressing communications in BFL, called BCFL, and derives the convergence rate of BCFL with non-convex loss, to maximize the final model accuracy.

Blockchain Assisted Federated Learning over Wireless Channels: Dynamic Resource Allocation and Client Scheduling

This work proposes a novel BFL framework that features the integration of training and mining at the client side, and formulate a joint optimization problem of training client selection and resource allocation, and solves the long-term mixed integer non-linear programming based on a Lyapunov technique.

A Blockchain Based Federated Learning for Message Dissemination in Vehicular Networks

The proposed blockchain based federated learning results in more vehicles uploading their models in a given time, which can potentially lead to a more accurate model in less time as compared to the same solution without using blockchain.

Blockchain-enabled Server-less Federated Learning

As the results show, the synchronous setting leads to higher prediction accuracy than the asynchronous case, thus becoming an appealing solution for FL when dealing with large datasets, tough timing constraints, or highly varying training data.

FLoBC: A Decentralized Blockchain-Based Federated Learning Framework

This work demonstrates the solution FLoBC for building a generic decentralized federated learning system using the blockchain technology, accommodating any machine learning model that is compatible with gradient descent optimization.

Blockchain for federated learning toward secure distributed machine learning systems: a systemic survey

An in-depth survey of BCFL is introduced and discusses the insights of such a new paradigm, as well as improving FL performance with Blockchain and several combined applications of incentive mechanisms in FL.

On Dynamic Resource Allocation for Blockchain Assisted Federated Learning over Wireless Channels

  • Xiumei DengJun Li H. Poor
  • Computer Science
    2021 IEEE International Conferences on Internet of Things (iThings) and IEEE Green Computing & Communications (GreenCom) and IEEE Cyber, Physical & Social Computing (CPSCom) and IEEE Smart Data (SmartData) and IEEE Congress on Cybermatics (Cybermatics)
  • 2021
This work proposes a novel BFL framework that features the integration of training and mining at the client side, and obtains the closed-form solution by using the Lyapunov optimization method.

Latency Optimization for Blockchain-Empowered Federated Learning in Multi-Server Edge Computing

A novel deep reinforcement learning scheme with a parameterized advantage actor critic algorithm for blockchain-based federated learning in multi-server edge computing, which theoretically characterize the convergence properties of BFL in terms of the aggregation delay, mini-batch size, and number of P2P communication rounds.

Federated learning meets blockchain at 6G edge: a drone-assisted networking for disaster response

This work quantifies the probability of occurrence of forking events to analyze the uncertainty of the system towards the additional energy wastage, and develops pragmatic analyses of the expected energy consumption by considering the parameters like the number of miners as well as the power consumed during computing, block transfer and 6G channel dynamics.



A Decentralized Federated Learning Approach for Connected Autonomous Vehicles

This paper develops a mathematical framework that features the controllable network and BFL parameters, such as the retransmission limit, block size, block arrival rate, and the frame sizes, so as to capture their impact on the system-level performance.

Blockchained On-Device Federated Learning

An end-to-end latency model of BlockFL is analyzed and the optimal block generation rate is characterized by considering communication, computation, and consensus delays.

Blockchain-Enabled Wireless Internet of Things: Performance Analysis and Optimal Communication Node Deployment

An analytical model for the blockchain-enabled wireless IoT system is established and an algorithm to determine the optimal full function node deployment for blockchain system under the criterion of maximizing transaction throughput is designed.

Impacts of Mobility on Performance of Blockchain in VANET

This paper provides an analysis framework that formulates the impact of mobility on a blockchain system’s performance in a VANET based on three key metrics: the probability of a successful addition of block to the chain; the stability of a rendezvous, and the number of blocks exchanged during a Rendezvous.

Performance Analysis of Blockchain Systems With Wireless Mobile Miners

Simulation results verify the analytical derivations and show that using a larger number of MMs can reduce the energy consumption by up to 95% compared to a blockchain system with a single MM.

Deconstructing Blockchains: A Comprehensive Survey on Consensus, Membership and Structure

This paper proposes an evaluation framework with insight into system models, desired properties and analysis criteria, using the decoupled components as criteria, and uses this framework to provide clear and intuitive overviews of the design principles behind the analyzed systems and the properties achieved.

Cooperative and Distributed Computation Offloading for Blockchain-Empowered Industrial Internet of Things

This paper proposes a multihop cooperative and distributed computation offloading algorithm that considers the data processing tasks and the mining tasks together for blockchain-empowered IIoT and designs an efficient distributed algorithm based on exchanging messages betweenIIoT devices to achieve the NE with low computational complexity.

Corking by Forking: Vulnerability Analysis of Blockchain

The large deviation theory is employed to study the vulnerability of blockchain networks incurred by intentional forks from a micro point of view, boosting forward-looking and strategic planning mechanisms for resisting the forking attack.

Incentive Design for Efficient Federated Learning in Mobile Networks: A Contract Theory Approach

The contract theory is adopted to design an effective incentive mechanism for simulating the mobile devices with high-quality (i.e., high-accuracy) data to participate in federated learning with improved learning accuracy.

Distributed Federated Learning for Ultra-Reliable Low-Latency Vehicular Communications

The problem of joint power and resource allocation (JPRA) for ultra-reliable low-latency communication (URLLC) in vehicular networks is studied and a novel distributed approach based on federated learning (FL) is proposed to estimate the tail distribution of the queues.