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

arXiv: https://arxiv.org/abs/2211.10033 · HTML: https://mlsanity.com/paper/2211.10033/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 35 references that are in the map.
- First posted on arXiv 18 Nov 2022.

## Builds on (most cited first, 6 of 6)

- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks](https://mlsanity.com/paper/1701.04143/) (2017)
- [On the Vulnerability of CNN Classifiers in EEG-Based BCIs](https://mlsanity.com/paper/1904.01002/) (2019)
- [Universal Adversarial Perturbations for CNN Classifiers in EEG-Based BCIs](https://mlsanity.com/paper/1912.01171/) (2019)
- [EEG-Based Brain-Computer Interfaces Are Vulnerable to Backdoor Attacks](https://mlsanity.com/paper/2011.00101/) (2020)
- [Active Learning for Black-Box Adversarial Attacks in EEG-Based Brain-Computer Interfaces](https://mlsanity.com/paper/1911.04338/) (2019)

## Abstract (arXiv)

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 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.