User Identity Protection in EEG-based Brain-Computer Interfaces

TL;DR

This paper highlights a privacy vulnerability in EEG-based BCIs where user identity can be easily inferred, and proposes methods to anonymize EEG data while preserving its primary decoding function.

Contribution

It introduces two novel approaches to transform EEG data into identity-unlearnable form, significantly reducing user identification accuracy without impairing BCI performance.

Findings

User identification accuracy reduced from 70.01% to 21.36%.

Proposed methods effectively protect user privacy in EEG data.

Experiments conducted on seven datasets across five paradigms.

Abstract

A brain-computer interface (BCI) establishes a direct communication pathway between the brain and an external device. Electroencephalogram (EEG) is the most popular input signal in BCIs, due to its convenience and low cost. Most research on EEG-based BCIs focuses on the accurate decoding of EEG signals; however, EEG signals also contain rich private information, e.g., user identity, emotion, and so on, which should be protected. This paper first exposes a serious privacy problem in EEG-based BCIs, i.e., the user identity in EEG data can be easily learned so that different sessions of EEG data from the same user can be associated together to more reliably mine private information. To address this issue, we further propose two approaches to convert the original EEG data into identity-unlearnable EEG data, i.e., removing the user identity information while maintaining the good performance on the primary BCI task. Experiments on seven EEG datasets from five different BCI paradigms showed that on average the generated identity-unlearnable EEG data can reduce the user identification accuracy from 70.01\% to at most 21.36\%, greatly facilitating user privacy protection in EEG-based BCIs.