Visible to the public Cognitive Privacy: AI-enabled Privacy using EEG Signals in the Internet of Things

TitleCognitive Privacy: AI-enabled Privacy using EEG Signals in the Internet of Things
Publication TypeConference Paper
Year of Publication2020
AuthorsSchiliro, F., Moustafa, N., Beheshti, A.
Conference Name2020 IEEE 6th International Conference on Dependability in Sensor, Cloud and Big Data Systems and Application (DependSys)
Date PublishedDec. 2020
ISBN Number978-1-7281-7651-2
Keywordsartificial intelligence, Brain modeling, cognitive privacy, Data models, data privacy, eeg, electroencephalography, expert systems, human factors, IoT, neuroscience, Neurotechnology, privacy, psychology, pubcrawl, Scalability, Task Analysis

With the advent of Industry 4.0, the Internet of Things (IoT) and Artificial Intelligence (AI), smart entities are now able to read the minds of users via extracting cognitive patterns from electroencephalogram (EEG) signals. Such brain data may include users' experiences, emotions, motivations, and other previously private mental and psychological processes. Accordingly, users' cognitive privacy may be violated and the right to cognitive privacy should protect individuals against the unconsented intrusion by third parties into the brain data as well as against the unauthorized collection of those data. This has caused a growing concern among users and industry experts that laws to protect the right to cognitive liberty, right to mental privacy, right to mental integrity, and the right to psychological continuity. In this paper, we propose an AI-enabled EEG model, namely Cognitive Privacy, that aims to protect data and classifies users and their tasks from EEG data. We present a model that protects data from disclosure using normalized correlation analysis and classifies subjects (i.e., a multi-classification problem) and their tasks (i.e., eye open and eye close as a binary classification problem) using a long-short term memory (LSTM) deep learning approach. The model has been evaluated using the EEG data set of PhysioNet BCI, and the results have revealed its high performance of classifying users and their tasks with achieving high data privacy.

Citation Keyschiliro_cognitive_2020