Firefly algorithm based WSN-IoT security enhancement with machine learning for intrusion detection

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Jan. 2, 2024

Abstract A Wireless Sensor Network (WSN) aided by the Internet of Things (IoT) is a collaborative system WSN systems and IoT networks are work to exchange, gather, handle data. The primary objective this collaboration enhance data analysis automation facilitate improved decision-making. Securing with assistance necessitates implementation protective measures confirm safety reliability interconnected components. This research significantly advances current state art in security synergistically harnessing potential machine learning Firefly Algorithm. contributions twofold: firstly, proposed FA-ML technique exhibits an exceptional capability intrusion detection accuracy within WSN-IoT landscape. Secondly, amalgamation Algorithm introduces novel dimension domain security-oriented optimization techniques. implications resonate across various sectors, ranging from critical infrastructure protection industrial beyond, where safeguarding integrity paramount importance. cutting-edge bio-inspired algorithms marks pivotal step forward crafting robust intelligent for evolving landscape IoT-driven technologies. For WSN-IoT, method employs support vector (SVM) model classification parameter tuning accomplished using Grey Wolf Optimizer (GWO) algorithm. experimental evaluation simulated NSL-KDD Dataset, revealing remarkable enhancement technique, achieving maximum 99.34%. In comparison, KNN-PSO XGBoost models achieved lower accuracies 96.42% 95.36%, respectively. findings validate as active solution systems, power bolster capabilities.

Language: Английский

---

MalBoT-DRL: Malware Botnet Detection Using Deep Reinforcement Learning in IoT Networks

IEEE Internet of Things Journal, Journal Year: 2023, Volume and Issue: 11(6), P. 9610 - 9629

Published: Oct. 12, 2023

In the dynamic landscape of cyber threats, multi-stage malware botnets have surfaced as significant threats concern. These sophisticated can exploit Internet Things (IoT) devices to undertake an array cyberattacks, ranging from basic infections complex operations such phishing, cryptojacking, and distributed denial service (DDoS) attacks. Existing machine learning solutions are often constrained by their limited generalizability across various datasets inability adapt mutable patterns attacks in real world environments, a challenge known model drift. This limitation highlights pressing need for adaptive Intrusion Detection Systems (IDS), capable adjusting evolving threat new or unseen paper introduces MalBoT-DRL, robust botnet detector using deep reinforcement learning. Designed detect throughout entire lifecycle, MalBoT-DRL has better offers resilient solution integrates damped incremental statistics with attention rewards mechanism, combination that not been extensively explored literature. integration enables dynamically ever-changing within IoT environments. The performance validated via trace-driven experiments two representative datasets, MedBIoT N-BaIoT, resulting exceptional average detection rates 99.80% 99.40% early late phases, respectively. To best our knowledge, this work one first studies investigate efficacy enhancing IDS.

Language: Английский

---

FL-IDS: Federated Learning-Based Intrusion Detection System Using Edge Devices for Transportation IoT

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 52215 - 52226

Published: Jan. 1, 2024

A federated learning-based intrusion detection system (FL-IDS) is introduced in this paper to enhance the security of vehicular networks context IoT edge device implementations. The FL-IDS protects data privacy by using local learning, where devices share only model updates with an aggregation server. This server then generates enhanced model. also incorporates machine learning (ML) and deep (DL) classifiers, namely logistic regression (LR) convolutional neural (CNN), prevent attacks transportation environments. performance proposed IDS was evaluated two different datasets, NSL-KDD Car-Hacking. evaluation has been based on accuracy loss parameters. results showthat outperforms traditional centralized approaches regarding protection.

Language: Английский

---

Quantum-empowered federated learning and 6G wireless networks for IoT security: Concept, challenges and future directions

Future Generation Computer Systems, Journal Year: 2024, Volume and Issue: 160, P. 577 - 597

Published: June 13, 2024

The Internet of Things (IoT) has revolutionized various sectors by enabling seamless device interaction. However, the proliferation IoT devices also raised significant security and privacy concerns. Traditional measures often fail to address these concerns due unique characteristics networks, such as heterogeneity, scalability, resource constraints. This survey paper adopts a thematic exploration approach for comprehensive analysis investigate convergence quantum computing, federated learning, 6G wireless networks. novel intersection is explored significantly improve within ecosystem. To enable several secure, intelligent applications, with its superior computational capabilities, can strengthen encryption algorithms, making data more secure. Federated decentralized machine learning approach, allows learn shared model while keeping all training on original device, thereby enhancing privacy. synergy becomes even crucial when integrated high-speed, low-latency capabilities which facilitate real-time, secure processing communication among many devices. Second, we discuss latest developments, offering an up-to-date overview advanced solutions, available datasets, key performance metrics summarizing vital insights, challenges, trends in securing systems. Third, design conceptual framework integrating computing adapted Finally, highlight future advancements technologies networks summarize implications security, paving way researchers practitioners field security.

Language: Английский

---

Towards unbalanced multiclass intrusion detection with hybrid sampling methods and ensemble classification

Applied Soft Computing, Journal Year: 2024, Volume and Issue: 157, P. 111517 - 111517

Published: March 21, 2024

Intrusion Detection Systems (IDS) play a crucial role in securing computer networks against malicious activities. However, their efficacy is consistently hindered by the persistent challenge of class imbalance real-world datasets. While various methods, such as resampling techniques, ensemble cost-sensitive learning, data augmentation, and so on, have individually addressed classification issues, there exists notable gap literature for effective hybrid methodologies aimed at enhancing IDS performance. To bridge this gap, our research introduces an innovative methodology that integrates undersampling oversampling strategies within framework. This novel approach designed to harmonize dataset distributions optimize performance, particularly intricate multi-class scenarios. In-depth evaluations were conducted using well-established intrusion detection datasets, including Car Hacking: Attack Defense Challenge 2020 (CHADC2020) IoTID20. Our results showcase remarkable proposed methodology, revealing significant improvements precision, recall, F1-score metrics. Notably, hybrid-ensemble method demonstrated exemplary average F1 score exceeding 98% both underscoring its exceptional capability substantially enhance accuracy. In summary, represents contribution field IDS, providing robust solution pervasive imbalance. The framework not only strengthens but also illuminates seamless integration classifiers, paving way fortified network defenses.

Language: Английский

---

Advancements in training and deployment strategies for AI-based intrusion detection systems in IoT: a systematic literature review

Discover Internet of Things, Journal Year: 2025, Volume and Issue: 5(1)

Published: Jan. 22, 2025

Language: Английский

---

Optimizing Intrusion Detection for IoT: A Systematic Review of Machine Learning and Deep Learning Approaches With Feature Selection and Data Balancing

Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery, Journal Year: 2025, Volume and Issue: 15(2)

Published: March 28, 2025

ABSTRACT As the Internet of Things (IoT) continues expanding its footprint across various sectors, robust security systems to mitigate associated risks are more critical than ever. Intrusion Detection Systems (IDS) fundamental in safeguarding IoT infrastructures against malicious activities. This systematic review aims guide future research by addressing six pivotal questions that underscore development advanced IDS tailored for environments. Specifically, concentrates on applying machine learning (ML) and deep (DL) technologies enhance capabilities. It explores feature selection methodologies aimed at developing lightweight solutions both effective efficient scenarios. Additionally, assesses different datasets balancing techniques, which crucial training models perform accurately reliably. Through a comprehensive analysis existing literature, this highlights significant trends, identifies current gaps, suggests studies optimize frameworks ever‐evolving landscape.

Language: Английский

---

Evolving cybersecurity frontiers: A comprehensive survey on concept drift and feature dynamics aware machine and deep learning in intrusion detection systems

Engineering Applications of Artificial Intelligence, Journal Year: 2024, Volume and Issue: 137, P. 109143 - 109143

Published: Aug. 22, 2024

Language: Английский

---

A Hybrid Meta-heuristics Algorithm: XGBoost-Based Approach for IDS in IoT

SN Computer Science, Journal Year: 2024, Volume and Issue: 5(5)

Published: May 10, 2024

Language: Английский

---

Deep learning technology of computer network security detection based on artificial intelligence

Computers & Electrical Engineering, Journal Year: 2023, Volume and Issue: 110, P. 108813 - 108813

Published: June 15, 2023

Language: Английский

---