34th European Signal Processing Conference

Die 34th European Signal Processing Conference EUSIPCO findet vom 31. August bis 4. September 2026 in  Bruges, Belgien, statt. Das Fraunhofer IDMT wird aktuelle Forschungsergebnisse aus dem Bereich der datenschutzkonformen EEG Datenanonymisierung vorstellen.

Electroencephalography (EEG) is widely used for recording brain activity and has seen numerous applications in machine learning, such as detecting sleep stages and neurological disorders. Several studies have successfully shown the potential of EEG data for re-identification and leakage of other personal information. Therefore, the increasing availability of EEG consumer devices raises concerns about user privacy, motivating us to investigate how to safeguard this sensitive data while retaining its utility for EEG applications. To address this challenge, we propose a transformer-based autoencoder to create EEG data that does not allow for subject re-identification while still retaining its utility for specific machine learning tasks. 

We apply our approach to automatic sleep staging by evaluating the re-identification and utility potential of EEG data before and after anonymization. We expand on prior evaluations by also considering attackers trained on anonymized data. We show that the utility of the data can be preserved while destroying identifiability for attackers trained on original data, but that fresh attackers can still recover substantial, albeit reduced personal information.

Das Poster wird von Kay Fuhrmeister am 4. September 2026 zwischen 10:30 und 12:30 Uhr in der Session "BISA-P5: Electrophysiological Signal Feature Extraction, Classification, and Clinical Applications" präsentiert.

Diese Forschunsgarbeit wurde im Rahmen der Projekte NEMO und AVATAR-transfer durchgeführt.