SEMINAR S’23-Adversarial Stimuli: Attacking Brain-Computer Interfaces via Perturbed Sensory Events

• Post by: Bahareh Arghavani
• February 27, 2023
• Comments off

Presenter: Bibek Upadhayay(PhD Candidate – SAIL Lab)
Time: Friday 03/31/2023, 12 pm – 1 pm ET

Place: Buckman 233A
Recording: TBA

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.

Bio:

Bibek Upadhayay is a PhD student and Research Assistant in the SAIL Lab. His research focuses on natural language processing and deep learning, specifically in the areas of information retrieval, graph modeling, and multi-modal learning. Bibek has worked on projects involving the extraction of structured information from news articles reporting human trafficking events, as well as the classification of fake news using both style-based and network-centric models. His work has been published in various conferences and has practical implications for social issues.