Attack and anomaly detection in IoT sensors in IoT sites using machine learning approaches

Обнаружение атак и аномалий в датчиках Интернета вещей на объектах Интернета вещей с использованием методов машинного обучения
Md. Milon Islam, Md. Mahmudul Hasan, Md Ishrak Islam Zarif, M. M. A. Hashem
2019-05-20

IoT attack detectionIoT sensorsRandom Forestanomaly detectionmachine learning
Attack and anomaly detection in the Internet of Things (IoT) infrastructure is a rising concern in the domain of IoT. With the increased use of IoT infrastructure in every domain, threats and attacks in these infrastructures are also growing commensurately. Denial of Service, Data Type Probing, Malicious Control, Malicious Operation, Scan, Spying and Wrong Setup are such attacks and anomalies which can cause an IoT system failure. In this paper, performances of several machine learning models have been compared to predict attacks and anomalies on the IoT systems accurately. The machine learning (ML) algorithms that have been used here are Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and Artificial Neural Network (ANN). The evaluation metrics used in the comparison of performance are accuracy, precision, recall, f1 score, and area under the Receiver Operating Characteristic Curve. The system obtained 99.4% test accuracy for Decision Tree, Random Forest, and ANN. Though these techniques have the same accuracy, other metrics prove that Random Forest performs comparatively better.
1
Decision Tree, Random Forest, and Artificial Neural Network achieved 99.4% test accuracy.
2
Despite equal accuracy, Random Forest performed comparatively better on the other evaluation metrics.
3
Models are compared using accuracy, precision, recall, F1 score, and area under the Receiver Operating Characteristic Curve.
4
The evaluated threats include Denial of Service, Data Type Probing, Malicious Control, Malicious Operation, Scan, Spying, and Wrong Setup.
5
The study compares Logistic Regression, Support Vector Machine, Decision Tree, Random Forest, and Artificial Neural Network models for detecting IoT attacks and anomalies.

IoT sensors and systems in IoT infrastructures/sites

Detection and classification performance for attacks and anomalies, including comparative machine-learning model effectiveness

Publication Details
Publication Date
2019-05-20
Journal
Publisher
ISSN
Cited by
1008
Access Type
Author Information
Authors
Md. Milon Islam
Md. Mahmudul Hasan
Md Ishrak Islam Zarif
M. M. A. Hashem
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%