Malicious Anomaly Detection and Prediction Using Prophet Luminol and RNN

R. Suganya, Sashikanth Reddy Avula, Balasubramanian Prabhu Kavin, Priyan Malarvizhi Kumar, Jeeva Selvaraj, Gan Hong Seng

Research output: Chapter in Book or Report/Conference proceedingChapterpeer-review

Abstract

Machine learning (ML) has brought about many advancements in today's world which is benefiting humans and machines. Because of the growth of digital services, malicious anomalies have increased on the transmission media. This has compromised crucial and important data of several organizations and companies. Vulnerabilities in network have increased in recent years and problems such as loss of data have increased. The process of detecting anomalies in network traffic becomes very important activity. An effective system for detection of these anomalies should be utilized to stop such attacks. Machine learning mechanisms for anomaly detection can prove to be the most accurate and best form of detecting malware or botnets on network so that we can prevent further threats. In this work one can understand the new implementation methods for anomaly detection. By importing python libraries and building ML models, one can learn certain outliers and different anomalies presence.

Original languageEnglish
Title of host publicationUtilizing AI in Network and Mobile Security for Threat Detection and Prevention
PublisherIGI Global
Pages81-95
Number of pages15
ISBN (Electronic)9798369399217
ISBN (Print)9798369399194
DOIs
Publication statusPublished - 1 Jan 2025

Fingerprint

Dive into the research topics of 'Malicious Anomaly Detection and Prediction Using Prophet Luminol and RNN'. Together they form a unique fingerprint.

Cite this