A blockchain-based decentralized machine learning framework for collaborative intrusion detection within UAVs

Ammar Ahmed Khan, Muhammad Mubashir Khan, Kashif Mehboob Khan, Junaid Arshad, Farhan Ahmad

Research output: Contribution to journalArticlepeer-review

44 Citations (Scopus)

Abstract

UAVs have numerous emerging applications in various domains of life. However, it is extremely challenging to gain the required level of public acceptance of UAVs without proving safety and security for human life. Conventional UAVs mostly depend upon the centralized server to perform data processing with complex machine learning algorithms. In fact, all the conventional cyber attacks are applicable on the transmission and storage of data in UAVs. While their impact is extremely serious because UAVs are highly dependent on smart systems that extensively utilize machine learning techniques in order to take decisions in human absence. In this regard, we propose to enhance the performance of UAVs with a decentralized machine learning framework based on blockchain. The proposed framework has the potential to significantly enhance the integrity and storage of data for intelligent decision making among multiple UAVs. We present the use of blockchain to achieve decentralized predictive analytics and present a framework that can successfully apply and share machine learning models in a decentralized manner. We evaluate our system using collaborative intrusion detection as a case-study in order to highlight the feasibility and effectiveness of using blockchain based decentralized machine learning approach in UAVs and other similar applications.

Original languageEnglish
Article number108217
Number of pages13
JournalComputer Networks
Volume196
Early online date18 Jun 2021
DOIs
Publication statusPublished - 4 Sep 2021
Externally publishedYes

Cite this