Adversarial Filtering Based Evasion and Backdoor Attacks to EEG-Based Brain-Computer Interfaces

TL;DR

This paper introduces adversarial filtering attacks on EEG-based brain-computer interfaces, revealing security vulnerabilities and emphasizing the need for enhanced protection in BCI systems.

Contribution

First to propose adversarial filtering methods for EEG-based BCIs, demonstrating their effectiveness and raising awareness of security risks in BCI applications.

Findings

Attacks successfully deceive BCI models across multiple datasets.

Adversarial filtering is easy to implement and effective.

Highlights security vulnerabilities in EEG-based BCIs.

Abstract

A brain-computer interface (BCI) enables direct communication between the brain and an external device. Electroencephalogram (EEG) is a common input signal for BCIs, due to its convenience and low cost. Most research on EEG-based BCIs focuses on the accurate decoding of EEG signals, while ignoring their security. Recent studies have shown that machine learning models in BCIs are vulnerable to adversarial attacks. This paper proposes adversarial filtering based evasion and backdoor attacks to EEG-based BCIs, which are very easy to implement. Experiments on three datasets from different BCI paradigms demonstrated the effectiveness of our proposed attack approaches. To our knowledge, this is the first study on adversarial filtering for EEG-based BCIs, raising a new security concern and calling for more attention on the security of BCIs.