article · International Journal of Computer Applications
The rapid proliferation of connected household devices increases exposure to cyber threats, creating a demand for robust security solutions. To address this risk, an intrusion detection system designed for multi-user smart home environments employs a four-layer architecture comprising packet capture, feature extraction, machine learning models, and an automated alert system. The design integrates data integrity countermeasures, including digital signatures and structured key management, to safeguard communication while providing immediate notifications to administrators when anomalies occur. Evaluated using simulated transmission control protocol and internet protocol connection records obtained from Kaggle, the integrated approach outperformed classical intrusion detection methods and earlier benchmarks in spotting anomalous network behaviour, delivering a comprehensive defence model for smart domestic environments.
Smart homes increasingly rely on interconnected devices that can be vulnerable to malicious intrusion. By combining automated anomaly detection with data protection techniques such as digital signatures, network monitors can spot unusual activity rapidly and notify administrators immediately. This helps prevent unauthorised access and protects domestic connected systems from being compromised.
The system could be incorporated into smart home cybersecurity software, router firmware, or third-party home security monitoring platforms for residential network administrators. Because the system was evaluated on simulated connection data from Kaggle rather than deployed on live domestic hardware, the technology appears to be at an early stage of research and validation.
AI-generated from the published abstract. Always read the original work before citing.
The fast increase in the number of Internet of Things (IoT) devices in smart homes makes them more exposed to cybersecurity threats.In turn, this creates an urgent need for robust intrusion detection systems.This study proposes an IoT Smart Home Multi User Access Control Intrusion Detection System (SHMUACIDS), with a view to improving the security by more efficiently detecting anomalies.It was designed based on a multi-layer architecture that consists of a Packet Capture Layer, a Feature Extraction Layer, the Machine Learning Model, and the Alerting System, all knitted together to work in tandem for proactively meeting the security challenges in IoT smart home environments.Intrusion Detection Data were obtained from kaggle website containing list of simulated TCP/IP connections were employed in training different machine learning models.The methodology also embeds digital signatures and proper key management, data integrity countermeasures together with an alert system which immediately notifies administrators on the detected anomalies.Results indicated that SHMUACIDS considerably outperformed the detection of anomalous activities in smart home IoT environments compared to some classical methods and previous studies.This holistic approach makes SHMUACIDS competitive in the smart home cybersecurity landscape.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.5120/ijca2025924607
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
