Sleep wearable firms trained AI on customer brainwaves without clear consent
Investigators found tens of millions of hours of EEG; Interaxon trained a model on about 50,000 hours.
Stories per day · 30 days
Relatedmuse2privacy2training-data2adversarial-robustness1bci1biosignals1brain-computer-interface1consent1ecg1eegnet1eye-tracking1foundation-models1hierarchical-alignment1interaxon1model-compression1multimodal1neurotech1non-invasive-bci1
10 stories, newest first · one card per story
Stories tagged #eeg
PhysioWave-T cuts biosignal token length with wavelet scale folding
A 30M EEG encoder leads 8 of 9 metrics versus BENDR, BIOT, LaBraM and EEGPT, and RALF lifts seizure sensitivity from 61.4% to 74.4%.
Hierarchical EEG-to-text alignment for sentence-level decoding
A novel hierarchical alignment framework retrieves read sentences from EEG signals and context for brain-computer interfaces.
ORBITAL compresses EEG decoders under a robustness constraint
S25-TRADES reached 23.06% mean true-union robustness versus 21.27% for uncompressed Full EEGNet.
EEGazeNet uses EEG to refine visual-search attention prediction
The public EEGaze 140 set pairs EEG and eye tracking from 36 people across 140 realistic scenes.
DyssomniaNN: Multi-Scale Spiking Neural Modeling of Human Sleep Disorders and Perceived Restedness
Researchers introduce DyssomniaNN, a spiking model of five sleep-disorder cohorts showing sleep time poorly predicts restedness.
What masking geometry works best for EEG foundation models?
An EEG masking ablation matches REVE-level decoding performance at a fraction of the pre-training compute.
AERIAL: Adversarial Evaluation of Robustness in Accuracy-Preserving Low-Precision EEG Decoders
A research paper on low-precision EEG decoders examines adversarial robustness across compression techniques.
Differentially Private EEG Feature Anonymization: A Privacy-Utility Case Study in Clinical Neurophysiology
Case study applies Gaussian and Laplace differential privacy to clinical EEG features, quantifying privacy-utility trade-offs across three deployment scenarios.
NERVE Attacks: Breaking AI-Powered Brain-Computer Interfaces
Researchers characterize NERVE, five attack dimensions against AI-powered brain-computer interfaces, and release the EEGle framework uncovering 17 attack instances.