Abstract :

The Rapid Growth Of Internet-connected Devices, Cloud Computing, And IoT Technologies Has Significantly Increased The Risk Of Cyberattacks, Particularly Botnet-based Threats. Botnets Consist Of Compromised Devices That Are Remotely Controlled By Attackers To Perform Malicious Activities Such As Distributed Denial-of-service Attacks, Data Theft, And Spam Distribution. Traditional Intrusion Detection Systems Rely Mainly On Signaturebased Or Rule-based Mechanisms, Which Are Ineffective In Identifying Modern Botnets Due To Their Dynamic Nature, Encrypted Communication, And Evolving Attack Strategies. To Address These Challenges, This Research Proposes An Artificial Intelligence-based Botnet Detection System Using Long Short-Term Memory (LSTM) Networks. The System Analyzes Sequential Network Traffic Data And Learns Temporal Behavioral Patterns To Distinguish Between Normal And Malicious Traffic. Network Flow Features Such As Packet Rate, Protocol Type, Connection Duration, And Traffic Behavior Are Extracted And Processed To Form Time-series Inputs For The Deep Learning Model. By Leveraging The Memory Capabilities Of LSTM, The System Effectively Identifies Hidden Patterns In Traffic Sequences And Detects Botnet Activity With High Accuracy. The Proposed Approach Demonstrates Improved Detection Performance And Reduced False Positive Rates Compared To Traditional Machine Learning Models. Furthermore, The System Is Scalable And Adaptable To Dynamic Network Environments, Enabling It To Detect Both Known And Previously Unseen Botnet Attacks. This Study Highlights The Potential Of Deep Learning Techniques In Strengthening Cybersecurity Defenses Against Sophisticated And Evolving Cyber Threats.

Published:

13-2-2026

Issue:

Vol. 26 No. 2 (2026)

Page Nos:

358-365

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite