Cybersecurity risk mitigation and network anomaly detection in smart homes using machine learning and data mining


Abstract

The rapid proliferation of Internet of Things (IoT) devices in smart home environments has significantly increased cybersecurity risks, necessitating the development of intelligent, adaptive, and proactive threat mitigation solutions. Traditional signature-based Intrusion Detection Systems (IDS) and rule-based anomaly detection techniques exhibit significant limitations in detecting zero-day attacks, adversarial intrusions, and evolving cyber threats. To address these challenges, this research proposes a Reinforcement Learning-Based Adaptive Threat Mitigation (RL-ATM) model, designed to enhance cybersecurity risk mitigation and network anomaly detection in smart homes by leveraging reinforcement learning, deep learning, and data mining techniques. Experimental evaluations confirm that RL-ATM significantly outperforms existing cybersecurity solutions, including signature-based IDS, anomaly-based machine learning models, and deep reinforcement learning (DRL) architectures. The proposed model achieved an accuracy of 98.87%, a precision of 97.49%, a recall of 98.36%, and a reduced false positive rate (FPR) of 1.8%, establishing itself as a highly reliable cybersecurity framework for real-world smart home applications. Comparative analysis reveals that traditional IDS models exhibit an accuracy of only 87.42% with an FPR of 6.3%, while anomaly-based ML techniques improve accuracy to 91.15% but still suffer from an FPR of 4.9%. The hybrid CNN + Reinforcement Learning models achieve 92.84% accuracy but lack real-time adaptability to dynamic attack landscapes, making RL-ATM the superior alternative in terms of detection reliability and adaptive response capabilities. This study makes a significant contribution to smart home cybersecurity, providing a highly scalable, adaptive, and autonomous AI-driven security framework capable of mitigating evolving cyber threats in real-time.
Ask to review this manuscript

Notes for potential reviewers

  • Volunteering is not a guarantee that you will be asked to review. There are many reasons: reviewers must be qualified, there should be no conflicts of interest, a minimum of two reviewers have already accepted an invitation, etc.
  • This is NOT OPEN peer review. The review is single-blind, and all recommendations are sent privately to the Academic Editor handling the manuscript. All reviews are published and reviewers can choose to sign their reviews.
  • What happens after volunteering? It may be a few days before you receive an invitation to review with further instructions. You will need to accept the invitation to then become an official referee for the manuscript. If you do not receive an invitation it is for one of many possible reasons as noted above.

  • PeerJ Computer Science does not judge submissions based on subjective measures such as novelty, impact or degree of advance. Effectively, reviewers are asked to comment on whether or not the submission is scientifically and technically sound and therefore deserves to join the scientific literature. Our Peer Review criteria can be found on the "Editorial Criteria" page - reviewers are specifically asked to comment on 3 broad areas: "Basic Reporting", "Experimental Design" and "Validity of the Findings".
  • Reviewers are expected to comment in a timely, professional, and constructive manner.
  • Until the article is published, reviewers must regard all information relating to the submission as strictly confidential.
  • When submitting a review, reviewers are given the option to "sign" their review (i.e. to associate their name with their comments). Otherwise, all review comments remain anonymous.
  • All reviews of published articles are published. This includes manuscript files, peer review comments, author rebuttals and revised materials.
  • Each time a decision is made by the Academic Editor, each reviewer will receive a copy of the Decision Letter (which will include the comments of all reviewers).

If you have any questions about submitting your review, please email us at [email protected].