NORMA eResearch @NCI Library

Evaluating Smart Contract Vulnerabilities through the Comparative Analysis of CNN, EfficientNet B2, and Xception Algorithms

-, Mohammed Shahimshah (2024) Evaluating Smart Contract Vulnerabilities through the Comparative Analysis of CNN, EfficientNet B2, and Xception Algorithms. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (798kB) | Preview
[thumbnail of Configuration Manual]
Preview
PDF (Configuration Manual)
Download (451kB) | Preview

Abstract

Smart contracts are critical to blockchain's trustless transactions, yet they remain susceptible to security breaches. This thesis explores the efficacy of convolutional neural networks (CNN), EfficientNet B2, and Xception algorithms in detecting vulnerabilities within smart contracts. Motivated by the necessity for improved security protocols, this research adapts these sophisticated pattern recognition algorithms to the unique context of smart contracts. The comparative analysis demonstrates that the CNN algorithm was in identifying typical security issues, whereas EfficientNet B2 and Xception are especially skilled at detecting intricate vulnerabilities. The study's findings indicate that the selection of an algorithm should be customized to address the particular security vulnerability of the smart contract under consideration. This work not only showcases the unique capabilities of the algorithms, but also offers valuable insights on how to develop more robust and dependable end user-system that can be utilized by everyone. This thesis examines the application of advanced algorithms for smart contract security within blockchain systems. It introduces a Flask-based web application tailored for vulnerability detection. The study reveals that the EfficientNet B2 algorithm achieved an 79% accuracy in identifying vulnerabilities, while the Xception algorithm recorded 69% accuracy. These findings validate the potential of the EfficientNet B2 algorithm in strengthening blockchain security.

Item Type: Thesis (Masters)
Supervisors:
Name
Email
Lugones, Diego
UNSPECIFIED
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Algebra > Algorithms > Computer algorithms
Q Science > QA Mathematics > Computer software > Computer Security
T Technology > T Technology (General) > Information Technology > Computer software > Computer Security
Divisions: School of Computing > Master of Science in Cyber Security
Depositing User: Ciara O'Brien
Date Deposited: 03 Jun 2025 14:45
Last Modified: 03 Jun 2025 14:45
URI: https://norma.ncirl.ie/id/eprint/7732

Actions (login required)

View Item View Item