Enhancing Cybersecurity in the Internet of Things Environment Using Bald Eagle Search Optimization With Hybrid Deep Learning

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 8337 - 8345

Published: Jan. 1, 2024

Nowadays, the Internet of Things (IoT) has become a rapid development; it can be employed by cyber threats in IoT devices. A correct system to recognize malicious attacks at platforms became major importance minimize security Botnet have more severe and common is threaten These interrupt alteration interrupting networks services for Several existing methods present themselves determine unknown patterns improving security. Recent analysis presents DL ML classifying detecting botnet from environment. Consequently, this paper develops Bald Eagle Search Optimization with Hybrid Deep Learning based detection (BESO-HDLBD) algorithm an platform. The presented BESO-HDLBD approach aims resolve issue identifying botnets To reduce high dimensionality problem, method uses BESO feature selection process. For purposes, HDL, which integration convolutional neural (CNNs), bidirectional long short-term memory (BiLSTM), attention concept. desire HDL technique utilises intricate nature that frequently contain difficult developing patterns. Combining CNNs permits effectual extraction spatial data, BiLSTM capture temporal dependencies, mechanisms improve model's capability concentrate on fundamental hyperparameters takes place using dragonfly (DFA). experimental could examined under benchmark dataset. obtained outcome infers better compared recent respect distinct estimation measures.

Language: Английский

---

A hybrid approach for efficient feature selection in anomaly intrusion detection for IoT networks

The Journal of Supercomputing, Journal Year: 2024, Volume and Issue: 80(19), P. 26942 - 26984

Published: Aug. 29, 2024

Abstract The exponential growth of Internet Things (IoT) devices underscores the need for robust security measures against cyber-attacks. Extensive research in IoT community has centered on effective traffic detection models, with a particular focus anomaly intrusion systems (AIDS). This paper specifically addresses preprocessing stage datasets and feature selection approaches to reduce complexity data. goal is develop an efficient AIDS that strikes balance between high accuracy low time. To achieve this goal, we propose hybrid approach combines filter wrapper methods. integrated into two-level system. At level 1, our classifies network packets normal or attack, 2 further classifying attack determine its specific category. One critical aspect consider imbalance these datasets, which addressed using Synthetic Minority Over-sampling Technique (SMOTE). evaluate how selected features affect performance machine learning model across different algorithms, namely Decision Tree, Random Forest, Gaussian Naive Bayes, k-Nearest Neighbor, employ benchmark datasets: BoT-IoT, TON-IoT, CIC-DDoS2019. Evaluation metrics encompass accuracy, precision, recall, F1-score. Results indicate decision tree achieves ranging 99.82 100%, short times 0.02 0.15 s, outperforming existing architectures networks establishing superiority achieving both times.

Language: Английский

---

Hybrid Sine-Cosine Chimp optimization based feature selection with deep learning model for threat detection in IoT sensor networks

Alexandria Engineering Journal, Journal Year: 2024, Volume and Issue: 102, P. 169 - 178

Published: June 7, 2024

Language: Английский

---

Meta‐analysis and systematic review for anomaly network intrusion detection systems: Detection methods, dataset, validation methodology, and challenges

IET Networks, Journal Year: 2024, Volume and Issue: 13(5-6), P. 339 - 376

Published: June 18, 2024

Abstract Intrusion detection systems built on artificial intelligence (AI) are presented as latent mechanisms for actively detecting fresh attacks over a complex network. The authors used qualitative method analysing and evaluating the performance of network intrusion system (NIDS) in systematic way. However, their approach has limitations it only identifies gaps by summarising data comparisons without considering quantitative measurements NIDS's performance. provide detailed discussion various deep learning (DL) methods explain networks based an infrastructure attack types. authors’ main contribution is review that utilises meta‐analysis to in‐depth analysis DL traditional machine (ML) notable recent works. assess validation methodologies clarify trends related dataset intrusion, detected attacks, classification tasks improve ML NIDS‐based publications. Finally, challenges future developments discussed pose new risks complexities security.

Language: Английский

---

Modeling of Intrusion Detection System Using Double Adaptive Weighting Arithmetic Optimization Algorithm with Deep Learning on Internet of Things Environment

Brazilian Archives of Biology and Technology, Journal Year: 2024, Volume and Issue: 67

Published: Jan. 1, 2024

Language: Английский

---

Review of filtering based feature selection for Botnet detection in the Internet of Things

Artificial Intelligence Review, Journal Year: 2025, Volume and Issue: 58(4)

Published: Jan. 31, 2025

Abstract Botnets are a major security threat in the Internet of Things (IoT), posing significant risks to user privacy, network availability, and integrity IoT devices. With increasing availability large datasets that contain hundreds or even thousands variables, selecting right set features can be challenging task. Feature selection is critical step developing effective machine learning-based botnet detection systems, as it enables subset most relevant for detection. This paper provides comprehensive review filtering based feature techniques IoT. It examines range evaluates their effectiveness addressing challenges limitations aims identify gaps literature areas future research, discuss broader implications findings field valuable insights guidance researchers practitioners working on IoT, highlights importance robust reliable systems.

Language: Английский

---

Ensemble Feature Engineering and Deep Learning for Botnet Attacks Detection in the Internet of Things

Transactions on Emerging Telecommunications Technologies, Journal Year: 2025, Volume and Issue: 36(3)

Published: March 1, 2025

ABSTRACT The Internet of Things (IoT) has revolutionized how people involve with technological innovations. However, this development also brought up significant security concerns. increasing number IoT attacks poses a serious risk to individuals and businesses equally. In response, article introduces an ensemble feature engineering method for effective selection, based on systematic behavioral analysis by means artificial intelligence. This identifies highlights the most relevant features from botnet dataset, facilitating accurate detection both malicious benign traffic. To detect attacks, incorporates distinct approaches, including genetic algorithm‐based approach, filter selection methods such as mutual information, LASSO regularization, forward‐backward search. A merger approach then combines these results, addressing redundancy irrelevance. As well, wrapper algorithm called recursive removal is applied further refine process. effectiveness selected set validated deep learning algorithms (CNN, RNN, LSTM, GRU) rooted in intelligence, IoT‐Botnet 2020 dataset. Results demonstrate encouraging performance, precision between 97.88% 98.99%, recall scores 99.10% 99.95%, accuracy 98.05% 99.21%, F1‐score ranging 98.45% 99.82%. Moreover, achieved 98.26%, score 99.68%, 98.49%, F1‐measure 99.00%, AUC‐ROC 82.37% specificity 98.38%. These outcomes highlight method's robust performance identifying

Language: Английский

---

A New Model to Evaluate Signature and Anomaly Based Intrusion Detection in Medical IoT System Using Ensemble Approach

SN Computer Science, Journal Year: 2025, Volume and Issue: 6(4)

Published: April 3, 2025

Language: Английский

---

Leveraging Federated Learning for DoS Attack Detection in IoT Networks Based on Ensemble Feature Selection and Deep Learning Models

Cyber Security and Applications, Journal Year: 2025, Volume and Issue: unknown, P. 100098 - 100098

Published: April 1, 2025

Language: Английский

---

A Hybrid Feature Selection Model for Anomaly-Based Intrusion Detection in IoT Networks

2022 International Telecommunications Conference (ITC-Egypt), Journal Year: 2024, Volume and Issue: unknown, P. 1 - 7

Published: July 22, 2024

Language: Английский

---