Securing IoT Environments from Botnets An Advanced Intrusion Detection Framework Using TJO-Based Feature Selection and Tree Growth Algorithm-Enhanced LSTM

Jul 16, 2026

Rising cyberattacks endanger IoT ecosystems, where botnet infections and continuously changing attack paths make identification difficult. The framework addresses the limits of traditional rule-based network intrusion detection that struggles with diverse IoT traffic and evolving malicious behavior. It applies transfer-learning dataset selection by choosing an appropriate source domain. Tom and Jerry Optimiser (TJO) selects the most relevant attributes from preprocessed data, then Tree Growth Algorithm (TGA) guides fine-tuning of Optimised LSTM. Evaluation shows improved detection accuracy.

LanguageEnglish

CategoryResearch & Report

FormatDOCX

Pages7

Reading Time18 min

Abstract

Introduction

Securing IoT Environments from Botnets: An Advanced Intrusion Detection Framework Using TJO-Based Feature Selection and Tree Growth Algorithm-Enhanced LSTM Ramya Vani Rayala Graduate Student, University of the Cumberlands, United States ramyavanirayala@gmail.com Piyush Kumar Pareek Department of AIML Nitte Meenakshi Institute of Technology, Bengaluru piyush.kumar@nmit.ac.in Chandrakanth Reddy Borra Graduate Student, University of the Cumberlands, United States HYPERLINK "mailto:chandu126099@gmail.com" chandu126099@gmail.com Srinivas Cheekati Graduate Student, University of the Cumberlands, United States HYPERLINK "mailto:scheekati10826@gmail.com" scheekati10826@gmail.com Abstract Concerns about cyberattacks are on the rise in the modern digital era, particularly with the expansion of the Internet of Things (IoT). Protecting IoT environments from harmful behaviour requires cybersecurity intrusion detection solutions. The ever-changing nature of infections and the proliferation of attack routes make botnet identification a formidable challenge. Numerous network devices have been targeted by botnet assaults, resulting in significant losses across several industries, due to the fast development of the IoT. Threats posed by botnets to network security are real, and deep learning models have demonstrated promise in efficiently detecting botnet activity in data collected from network traffic. Because of their remarkable capacity to autonomously discover intricate patterns and characteristics inside massive datasets. Unfortunately, the increasingly diverse nature of IoT ecosystems is rendering ineffective the traditional network-level intrusion detection solutions that rely on pre-defined rule sets. A framework to address this issue is presented in this study. When determining if a dataset is suitable for use in transfer learning, our suggested methodology encourages using that dataset as the source domain. The attributes that are most relevant are selected from the pre-processed data using Tom and Jerry Optimiser (TJO). Next, the prediction procedure makes use of Optimised Long-Short Term Memory (LSTM), with Tree Growth Algorithm (TGA) taking LSTM fine-tuning into account. The purpose of this selection procedure is to ascertain whether or not the suggested model is suitable for implementation, providing the optimal course of action in such cases. By selecting an appropriate source domain data set, our evaluation shows that the suggested framework achieves the best accuracy. Keywords: Cybersecurity intrusion detection systems; Tree Growth Algorithm; Tom and Jerry Optimizer; Optimized Long-Short Term Memory; Botnet attacks; Internet of Things. Introduction The widespread besides quick adoption of Internet technology for everyday, social, cultural, and institutional activities was a direct result of its meteoric rise [1]. Like other technologies, the internet can be used for malicious purposes, such as stealing money or personal information from unsuspecting individuals. Detecting botnet attacks is an important part of cyber defence since it helps to avoid or lessen many different kinds of online security threats [2]. Networks and data can be protected from threats including distributed denial of service (DDoS) attacks, data breaches, and malware propagation when security specialists find and eliminate botnets [3]. Not only does early detection reduce the likelihood of harm, but it also maintains the efficiency of the network and the trust that users have in digital services. On top of that, it encourages cyber resilience, ensures compliance with regulations, and backs innovation in the never-ending fight against cyber threats that are evolving on a global scale [4]. To swiftly identify and classify malicious botnet activity in network data, deep learning-based botnet discovery use robust machine learning representations [5]. Organisations can better safeguard their systems and data when they are able to detect botnet threats qu

FAQs

Why is botnet identification in IoT considered challenging?

Botnet infections evolve over time and attack routes proliferate, making signatures and patterns harder to maintain. IoT ecosystem diversity also reduces the effectiveness of traditional rule-based network intrusion detection.

How does the proposed framework choose the best transfer learning dataset?

The methodology encourages using the selected dataset as the source domain when it is suitable for transfer learning. This choice is part of the pipeline used to maximize overall detection performance.

What roles do TJO and TGA play in the model?

TJO performs attribute selection on preprocessed data to keep only the most relevant features. TGA supports Tree Growth Algorithm-enhanced LSTM fine-tuning during the prediction procedure.

Jul 16, 2026

Upload by Seraphina