Covariance transform reduces identity risk in motor imagery eeg data

Riemannian Suppression of Cross-Session Identity Leakage in Motor-Imagery EEG

Cryptography and Security

Summary

Motor-imagery EEG signals can reveal who a person is, even across multiple recording sessions, which raises privacy concerns. The authors developed a mathematical method that adjusts the core features of the EEG data to hide these personal identifiers without needing complex training or guessing models. Their technique greatly lowers the chance that someone can identify a person from their EEG data across sessions, while still keeping the important signals needed for brain-computer interface tasks mostly intact. This method was tested on public datasets and worked against various methods trying to reveal identities.

What this means in practice

  • For bci system developers: Improve EEG motor-imagery systems to protect user identity across sessions by integrating a covariance-based transform that suppresses personal information leakage without retraining models.
  • For medical device designers: Enhance EEG-based assistive devices to secure patient identity across sessions through a lightweight, non-training privacy-preserving data transformation.

Authors

Sheikh Samit Muhaimin, Aarthy Nagarajan

Abstract

Electroencephalography (EEG) recorded for motor-imagery (MI) brain-computer interfaces (BCIs) carries subject-identifying structure that persists across sessions, allowing separately released sessions from the same person to be linked. Existing EEG identity protections use learned or additive perturbations and operate on representations other than the covariance geometry underlying MI pipelines. We ask whether cross-session identity leakage can be suppressed directly in this covariance representation without learning a privacy model. We introduce a Riemannian transform that equalizes two subject-conditioned geometric statistics: the Riemannian mean covariance and the tangent-space scatter around it, with two optional band-specific refinements. Ablations show that mean alignment and scatter whitening carry nearly all of the suppression, while the optional stages contribute small, dataset-dependent refinements. Across two public datasets and five attackers spanning four covariance-space representations, the worst attacker falls from 90.8% to 15.6% on BCI Competition IV-2a and from 90.8% to 9.9% on OpenBMI, at a cost of 7.0 and 2.1 points of MI decoding accuracy relative to the 8-30 Hz input, and no aggregation rule exceeds chance by more than two points at any batch size. The transform requires no learned privacy model, surrogate network, or gradient-based training, and is fitted on one session and applied unchanged to a held-out later session.