Smart IoT Security: Lightweight Machine Learning Techniques for Multi-Class Attack Detection in IoT Networks

• URL: http://arxiv.org/abs/2502.04057v2
• Date: Sun, 15 Jun 2025 09:22:08 GMT
• Title: Smart IoT Security: Lightweight Machine Learning Techniques for Multi-Class Attack Detection in IoT Networks
• Authors: Shahran Rahman Alve, Muhammad Zawad Mahmud, Samiha Islam, Md. Asaduzzaman Chowdhury, Jahirul Islam,
• Abstract summary: This study addresses the limitations of multi-class attack detection in IoT devices.<n>We propose new, lightweight ensemble methods grounded in robust machine learning frameworks.<n>We evaluate a wide array of contemporary machine learning algorithms to identify the optimal choice for safeguarding IoT environments.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As the Internet of Things (IoT) expands rapidly, ensuring secure networks to defend against diverse cyber threats becomes increasingly vital. This study addresses the limitations of multi-class attack detection in IoT devices by proposing new, lightweight ensemble methods grounded in robust machine learning frameworks. Leveraging the CICIoT 2023 dataset which features 34 distinct attack types across 10 categories. We systematically evaluated a wide array of contemporary machine learning algorithms to identify the optimal choice for safeguarding IoT environments. Focusing on classifier-based approaches, our research addresses the complex and heterogeneous nature of attack vectors found in IoT ecosystems. Among the evaluated models, the Decision Tree classifier achieved the highest performance, with 99.56\% accuracy and a 99.62\% F1 score, demonstrating strong, reliable threat detection capabilities. The Random Forest algorithm followed closely, attaining 98.22\% accuracy and a 98.24\% F1 score, further highlighting the effectiveness of machine learning in handling high-dimensional data. These findings underscore the significant promise of incorporating machine learning classifiers into IoT security defenses and inspire further exploration into scalable, keystroke-based attack detection. Our approach offers a novel pathway for developing sophisticated algorithms for resource-constrained IoT devices, achieving a critical balance between accuracy and efficiency. Overall, this work advances the field of IoT security by establishing a strong baseline and framework for the development of intelligent, adaptive security measures suitable for evolving IoT landscapes.

Related papers

• Leveraging Machine Learning Techniques in Intrusion Detection Systems for Internet of Things [11.185300073739098]
  Traditional Intrusion Detection Systems (IDS) often fall short in managing the dynamic and large-scale nature of IoT networks. This paper explores how Machine Learning (ML) and Deep Learning (DL) techniques can significantly enhance IDS performance in IoT environments.
  arXiv  Detail & Related papers  (2025-04-09T18:52:15Z)
• Intelligent IoT Attack Detection Design via ODLLM with Feature Ranking-based Knowledge Base [0.964942474860411]
  Internet of Things (IoT) devices have introduced significant cybersecurity challenges.<n>Traditional machine learning (ML) techniques often fall short in detecting such attacks due to the complexity of blended and evolving patterns.<n>We propose a novel framework leveraging On-Device Large Language Models (ODLLMs) augmented with fine-tuning and knowledge base (KB) integration for intelligent IoT network attack detection.
  arXiv  Detail & Related papers  (2025-03-27T16:41:57Z)
• Learning in Multiple Spaces: Few-Shot Network Attack Detection with Metric-Fused Prototypical Networks [47.18575262588692]
  We propose a novel Multi-Space Prototypical Learning framework tailored for few-shot attack detection.<n>By leveraging Polyak-averaged prototype generation, the framework stabilizes the learning process and effectively adapts to rare and zero-day attacks.<n> Experimental results on benchmark datasets demonstrate that MSPL outperforms traditional approaches in detecting low-profile and novel attack types.
  arXiv  Detail & Related papers  (2024-12-28T00:09:46Z)
• Optimized IoT Intrusion Detection using Machine Learning Technique [0.0]
  Intrusion detection systems (IDSs) are essential for defending against a variety of attacks.<n>The functional and physical diversity of IoT IDS systems causes significant issues.<n>For peculiarity-based IDS, this study proposes and implements a novel component selection and extraction strategy.
  arXiv  Detail & Related papers  (2024-12-03T21:23:54Z)
• Lightweight CNN-BiLSTM based Intrusion Detection Systems for Resource-Constrained IoT Devices [38.16309790239142]
  Intrusion Detection Systems (IDSs) have played a significant role in detecting and preventing cyber-attacks within traditional computing systems. The limited computational resources available on Internet of Things (IoT) devices make it challenging to deploy conventional computing-based IDSs. We propose a hybrid CNN architecture composed of a lightweight CNN and bidirectional LSTM (BiLSTM) to enhance the performance of IDS on the UNSW-NB15 dataset.
  arXiv  Detail & Related papers  (2024-06-04T20:36:21Z)
• FaultGuard: A Generative Approach to Resilient Fault Prediction in Smart Electrical Grids [53.2306792009435]
  FaultGuard is the first framework for fault type and zone classification resilient to adversarial attacks. We propose a low-complexity fault prediction model and an online adversarial training technique to enhance robustness. Our model outclasses the state-of-the-art for resilient fault prediction benchmarking, with an accuracy of up to 0.958.
  arXiv  Detail & Related papers  (2024-03-26T08:51:23Z)
• Effective Intrusion Detection in Heterogeneous Internet-of-Things Networks via Ensemble Knowledge Distillation-based Federated Learning [52.6706505729803]
  We introduce Federated Learning (FL) to collaboratively train a decentralized shared model of Intrusion Detection Systems (IDS) FLEKD enables a more flexible aggregation method than conventional model fusion techniques. Experiment results show that the proposed approach outperforms local training and traditional FL in terms of both speed and performance.
  arXiv  Detail & Related papers  (2024-01-22T14:16:37Z)
• Unraveling Attacks in Machine Learning-based IoT Ecosystems: A Survey and the Open Libraries Behind Them [9.55194238764852]
  The Internet of Things (IoT) has brought forth an era of unprecedented connectivity, with an estimated 80 billion smart devices expected to be in operation by the end of 2025. Machine Learning (ML) serves as a crucial technology, not only for analyzing IoT-generated data but also for diverse applications within the IoT ecosystem. This paper embarks on a comprehensive exploration of the security threats arising from ML's integration into various facets of IoT.
  arXiv  Detail & Related papers  (2024-01-22T06:52:35Z)
• Malware Detection in IOT Systems Using Machine Learning Techniques [0.0]
  This study introduces a CNN-LSTM hybrid model for IoT malware identification and evaluates its performance against established methods. The proposed approach achieved 95.5% accuracy, surpassing existing methods.
  arXiv  Detail & Related papers  (2023-12-29T17:02:54Z)
• Effective Intrusion Detection in Highly Imbalanced IoT Networks with Lightweight S2CGAN-IDS [48.353590166168686]
  Internet of Things (IoT) networks contain benign traffic far more than abnormal traffic, with some rare attacks. Most existing studies have been focused on sacrificing the detection rate of the majority class in order to improve the detection rate of the minority class. We propose a lightweight framework named S2CGAN-IDS to expand the number of minority categories in both data space and feature space.
  arXiv  Detail & Related papers  (2023-06-06T14:19:23Z)
• Poisoning Attacks in Federated Edge Learning for Digital Twin 6G-enabled IoTs: An Anticipatory Study [37.97034388920841]
  Federated edge learning can be essential in supporting privacy-preserving, artificial intelligence (AI)-enabled activities in digital twin 6G-enabled Internet of Things (IoT) environments. We propose an anticipatory study for poisoning attacks in federated edge learning for digital twin 6G-enabled IoT environments.
  arXiv  Detail & Related papers  (2023-03-21T11:12:17Z)
• Harris Hawks Feature Selection in Distributed Machine Learning for Secure IoT Environments [8.690178186919635]
  Internet of Things (IoT) applications can collect and transfer sensitive data. It is necessary to develop new methods to detect hacked IoT devices. This paper proposes a Feature Selection (FS) model based on Harris Hawks Optimization (HHO) and Random Weight Network (RWN) to detect IoT botnet attacks.
  arXiv  Detail & Related papers  (2023-02-20T09:38:12Z)
• Lightweight Collaborative Anomaly Detection for the IoT using Blockchain [40.52854197326305]
  Internet of things (IoT) devices tend to have many vulnerabilities which can be exploited by an attacker. Unsupervised techniques, such as anomaly detection, can be used to secure these devices in a plug-and-protect manner. We present a distributed IoT simulation platform, which consists of 48 Raspberry Pis.
  arXiv  Detail & Related papers  (2020-06-18T14:50:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.