ProfilIoT: a machine learning approach for IoT device identification based on network traffic analysis

By Yair Meidan, Michael Bohadana, Asaf Shabtai, J. Guarnizo, Martín Ochoa, Nils Ole Tippenhauer, Yuval Elovici. ACM Symposium on Applied Computing, 2017

407 citations recorded by the source corpus.

In this work we apply machine learning algorithms on network traffic data for accurate identification of IoT devices connected to a network. To train and evaluate the classifier, we collected and labeled network traffic data from nine distinct IoT devices, and PCs and smartphones. Using supervised learning, we trained a multi-stage meta classifier; in the first stage, the classifier can distinguish between traffic generated by IoT and non-IoT devices. In the second stage, each IoT device is associated a specific IoT device class. The overall IoT classification accuracy of our model is 99.281+.

Subfields: Artificial Intelligence, Computer Networks and Communications, Signal Processing

View Paper: https://www.semanticscholar.org/paper/371f7ac8d33a044b71d392638c81077b72030814

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Antonio J. Sánchez-Esguevillas
2. Mohammed Ali Al-Garadi
3. A. Al-Ali
4. Manuel Lopez-Martin
5. Amr M. Mohamed
6. Xiaojiang Du
7. Gautam Srivastava
8. Jaime Lloret

In Computer Networks and Communications

1. Xiaojiang Du
2. Elias Bou-Harb
3. Antonio J. Sánchez-Esguevillas
4. Mohammed Ali Al-Garadi
5. A. Al-Ali
6. Manuel Lopez-Martin
7. Nataliia Neshenko
8. Amr M. Mohamed

In Signal Processing

1. Antonio J. Sánchez-Esguevillas
2. Mohammed Ali Al-Garadi
3. A. Al-Ali
4. Amr M. Mohamed
5. Xiaojiang Du
6. Jaime Lloret
7. Mohsen Guizani
8. Petros Spachos

Citations in the corpus

• Network Traffic Classifier With Convolutional and Recurrent Neural Networks for Internet of Things (2017, background): “device identification [36], target detection in Wireless Sensor Networks (WSN) [37] or user priority based [38].”
• Effective Heart Disease Prediction Using Hybrid Machine Learning Techniques (2019, background): “We have also seen recent developments in machine learning ML techniques used for Internet of Things (IoT) as well [43].”
• A Survey of Machine and Deep Learning Methods for Internet of Things (IoT) Security (2018, methodology): “[256] implemented ML algorithms for precise IoT device identification by utilising network traffic features, which are then fed into a multi-stage classifier.”
• Machine Learning Based Solutions for Security of Internet of Things (IoT): A Survey (2020, methodology): “[153] used ML classifier algorithms for the identification of IoT devices.”
• Demystifying IoT Security: An Exhaustive Survey on IoT Vulnerabilities and a First Empirical Look on Internet-Scale IoT Exploitations (2019, background): “[145] leveraged network traffic analysis to classify IoT devices connected to an organization’s network.”