Adversarial Stimuli: Attacking Brain-Computer Interfaces via Perturbed Sensory Events

TL;DR

This paper investigates how small, carefully designed visual stimuli can disrupt EEG-based brain-computer interfaces, revealing vulnerabilities that are exacerbated under stress conditions.

Contribution

It introduces adversarial stimuli as a novel attack method against BCIs and demonstrates their effectiveness through preliminary experiments.

Findings

Adversarial stimuli significantly impair BCI performance (p=0.0003).

Stress conditions increase attack effectiveness.

Minor sensory perturbations can cause substantial system failures.

Abstract

Machine learning models are known to be vulnerable to adversarial perturbations in the input domain, causing incorrect predictions. Inspired by this phenomenon, we explore the feasibility of manipulating EEG-based Motor Imagery (MI) Brain Computer Interfaces (BCIs) via perturbations in sensory stimuli. Similar to adversarial examples, these \emph{adversarial stimuli} aim to exploit the limitations of the integrated brain-sensor-processing components of the BCI system in handling shifts in participants' response to changes in sensory stimuli. This paper proposes adversarial stimuli as an attack vector against BCIs, and reports the findings of preliminary experiments on the impact of visual adversarial stimuli on the integrity of EEG-based MI BCIs. Our findings suggest that minor adversarial stimuli can significantly deteriorate the performance of MI BCIs across all participants (p=0.0003). Additionally, our results indicate that such attacks are more effective in conditions with induced stress.