An Improved Sensor Anomaly Detection Method in IoT System using Federated Learning

Tran, Duc Hoang; Nguyen, Van-Linh; Utama, Ida Bagus Krishna Yoga; Jang, Yeong Min

doi:10.1109/icufn55119.2022.9829561

Cited by 4 publications

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the future scope, they proposed to explore the association of multi‐models as the association of faulty nodes are independent. This research 10 mainly focused on threats in IoT Cybersecurity in a smart city. The approach they used was intelligent enough to detect anomalies with a low false positive rate.…”

Section: Related Workmentioning

confidence: 99%

Anomaly detection in IoT environment using machine learning

Bilakanti,

Pasam,

Palakollu

et al. 2024

Security and Privacy

View full text Add to dashboard Cite

This research paper delves into the security concerns within Internet of Things (IoT) networks, emphasizing the need to safeguard the extensive data generated by interconnected physical devices. The presence of anomalies and faults in the sensors and devices deployed within IoT networks can significantly impact the functionality and outcomes of IoT systems. The primary focus of this study is the identification of anomalies in IoT devices arising sensor tampering, with an emphasis on the application of machine learning techniques. While supervised methods like one‐class SVM, Gaussian Naive Bayes, and XG Boost have proven effective in anomaly detection, there has been a noticeable scarcity of research employing unsupervised methods. This scarcity is mainly attributed to the absence of well‐defined ground truths for model training. This research takes an innovative approach by investigating the utility of unsupervised algorithms, including Isolation Forest and Local Outlier Factor, alongside supervised techniques to enhance the precision of anomaly detection.

show abstract

Section: Related Workmentioning

confidence: 99%