Adaptive Thresholds of EEG Brain Signals for IoT Devices Authentication

Abstract

In this paper, a new authentication method has been proposed for the Internet of Things (IoT) devices. This method is based on electroencephalography EEG signals, and hand gestures. The proposed EEG signals authentication method used a low price NeuroSky MindWave headset. This was based on choosing the adaptive thresholds of attention and meditation mode for the authentication key. Hand gestures to control authentication processes by using a general camera. To verify that a new authentication method is widely accepted, it must meet two main conditions, security and usability. The evaluation of the prototype usability was based on ISO 9241-11:2018 standards usability model. Results revealed that the proposed method demonstrated the usability of authentication by using EEG signals with the accuracy of 92%, the efficiency of 93%, and user satisfaction is acceptable and satisfying. To evaluate the security of the prototype, we consider the most important three threats related to IoT devices which they are guessing, physical observation, and targeted impersonation. The results showed that the password strength, using the proposed system is stronger than the traditional keyboard. The proposed authentication method also is resistant to target impersonation and physical observation.

Keywords

• Electroencephalography
• brain computer interface (BCI)
• convolutional neural networks (CNN)
• NeuroSky
• human computer interaction (HCI)
• hand gestures recognition