Advanced Cyber Security Threat Detection Using Deep Learning and Behavioral Analytics

Read full text Summarise with VIRAT
Authors: R. DINESH, S. JEEVITHAMBIGAI, V. SANDHIYA, S. KALAIVANI, T. SUSMITHA
Cited by: 0
References: 2

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

ABSTRACT The rapid growth of Fake image Detections has significantly increased the number and complexity of cyber threats such as Fake image Detections attacks, malware, insider threats, and zero-day vulnerabilities. Traditional rule-based cyber security systems often fail to detect sophisticated and evolving attack patterns due to their reliance on predefined signatures. This research proposes an advanced cyber security threat detection framework that integrates deep learning and behavioral analytics to enhance threat identification. Transformer-based models are employed to analyze large volumes of network traffic and system log data to detect abnormal behavioral patterns. Additionally, graph-based deep learning techniques are utilized to model relationships between users, devices, and network activities for identifying complex attack behaviors. The proposed system enables real-time monitoring and intelligent threat detection with improved accuracy. Experimental analysis demonstrates that the integration of behavioral analytics with deep learning significantly improves the detection capability for emerging and unknown cyber Threats. The system provides a scalable and proactive solution for modern cyber security infrastructures. Keywords: Fake Image detections security, Deep Learning, Behavioral Analytics, Transformer Models, Graph Neural Networks, Threat Detection, Network Security.

Fields of Study & Subjects

Network Security and Intrusion Detection Information and Cyber Security Spam and Phishing Detection

Publication details

Journal / source
INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT
Volume
10
Issue
03
Pages
1–9
Publication date
30 March 2026
Language
EN