Adversarial Stimuli: Attacking Brain-Computer Interfaces via Perturbed Sensory Events
Not on the map. Why?
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 6 of its 35 references that are in the map. First posted on arXiv 18 Nov 2022.
Builds on
6 of 35 references.
References · 6
- 2016Universal adversarial perturbationscited by 774
- 2017Vulnerability of Deep Reinforcement Learning to Policy Induction Attackscited by 91
- 2019On the Vulnerability of CNN Classifiers in EEG-Based BCIscited by 17
- 2019Universal Adversarial Perturbations for CNN Classifiers in EEG-Based BCIscited by 13
- 2020EEG-Based Brain-Computer Interfaces Are Vulnerable to Backdoor Attackscited by 12
- 2019Active Learning for Black-Box Adversarial Attacks in EEG-Based Brain-Computer Interfacescited by 3
Built on by
Not cited yet.