CIVILICA We Respect the Science
(ناشر تخصصی کنفرانسهای کشور / شماره مجوز انتشارات از وزارت فرهنگ و ارشاد اسلامی: ۸۹۷۱)

Providing a method to anomaly detection in blockchain patterns using a combination of genetic algorithm and machine learning

عنوان مقاله: Providing a method to anomaly detection in blockchain patterns using a combination of genetic algorithm and machine learning
شناسه ملی مقاله: METACONF01_039
منتشر شده در نخستین کنفرانس بین المللی فناوری متاورس، بلاک چین و ارز های دیجیتال در سال 1401
مشخصات نویسندگان مقاله:

Sina Yousefi - Final semester master's student in information technology engineering management
AliReza Honarvar - Supervisor and faculty member of Azad University, Safa Shahr branch

خلاصه مقاله:
Blockchain models are vulnerable to various types of attacks due to their vulnerability. Due to many network traffic features of blockchain patterns, machine learning models are time-consuming to identify attacks. In this paper, a new method for detecting anomalies in blockchain patterns is presented. The proposed method for network intrusion detection is to use machine learning technique and also to reduce the number of features in order to reduce the time of intrusion detection in blockchain patterns. At first in the proposed method is reduced the number of features using genetic algorithm, then it is made using classifications based on machine learning. The proposed method is tested on the NSL-KDD dataset. Accuracy, recall and correctness criteria are used to evaluate the proposed method. The accuracy of the proposed method is above ۹۷% in the best test mode, and its validity can be confirmed based on comparison with other references.

کلمات کلیدی:
Internet of Things, intrusion detection system, machine learning, feature selection

صفحه اختصاصی مقاله و دریافت فایل کامل: https://civilica.com/doc/1661521/