Evaluation of Blockchain Service Level Agreement (SLA) Using Hyperledger Fabric (HLF)

Authors

  • Dhivya K M.Tech Scholar, Department of Computer Science, Pondicherry University, Pondicherry, India Author
  • B Akoramurthy PhD Scholar, Department of Computer Science and Engineering, National Institute of TechnologyPuducherry, Karaikal, India Author
  • B Surendiran Associate Professor, Department of Computer Science and Engineering, National Institute of Technology - Pondicherry, Karaikal, India Author
  • T Sivakumar Assistant Professor, Department of Computer Science, Pondicherry University, Pondicherry, India Author

DOI:

https://doi.org/10.47392/irjash.2023.S013

Keywords:

Smart Contract, SLA, Hyperledger Fabric, Blockchain, LSTM

Abstract

Different sectors are being revolutionized by distributed ledger technology.
According to the 2022 market valuation, Hyperledger is now the second-largest
blockchain platform for smart contracts. The creation of numerous apps may
be sped up and simplified with smart contracts, but there are certain drawbacks as well. For instance, vulnerability contracts are created intentionally
to weaken candor, smart contracts are employed to conduct fraudulent activities, and there are many redundant contracts that squander the efficiency of
the system for no real reason. To solve these problems, we provide in this
research Service Level Agreement(SLA) for Hyperledger smart contracts. We
created Hyperledger smart contracts and focused on how smart contracts and
consumers used data. By manually analyzing the transactions, we were able
to extract four behavioral characteristics that may be used to differentiate
between various contract types. Then, a smart contract is built using these
to include 14 fundamental functionalities. We provide a data splitting algorithm for splitting the gathered smart contracts in order to create the experimental dataset. Then, we train and test our dataset using an LSTM network.
The comprehensive experimental findings demonstrate that our method can discriminate between various contract types and may be used to identify malicious
contracts and detect anomalies with acceptable precision, recall, and F1-score. 

Downloads

Published

2023-05-28