mlsanityData to 14 Oct 2026

Revisiting Privacy Preservation in Brain-Computer Interfaces: Conceptual Boundaries, Risk Pathways, and a Protection-Strength Grading Framework

arXiv 2605.11386 ↗First posted 12 May 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Brain-computer interfaces (BCIs) are moving rapidly from laboratory research into clinical, edge, and real-world settings. Under ISO/IEC 8663:2025, a BCI is a direct communication link between central nervous system activity and external software or hardware systems. This link expands privacy risk beyond raw neural-signal leakage: neural data, derived representations, model assets, and decoded outputs can be re-associated with individuals across collection, transmission, storage, training, inference, and feedback, or used to infer information beyond what a task requires. Starting from the general BCI paradigm, this review deffnes privacy-protection boundaries, protection objects, and the relationship between user data privacy and model privacy within a shared risk pathway. It then proposes a three-dimensional framework - protection object, lifecycle stage, and dominant protection-strength level - to classify existing work into four levels of protection strength. Finally, mental privacy and neuroethical risks are treated as open issues, emphasizing that BCI privacy protection should not only obscure data but also disentangle task-irrelevant sensitive information while preserving downstream utility. Keywords: Brain-computer interface, Neural data privacy, User data privacy, Model privacy, Disentanglement of task-irrelevant sensitive information, Protection-strength grading, Neuroethical risks

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 92 references that are in the map. First posted on arXiv 12 May 2026.

Builds on

14 of 92 references.

References · 14

  1. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 520
  2. 2018Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learningcited by 77
  3. 2022Are Your Sensitive Attributes Private? Novel Model Inversion Attribute Inference Attacks on Classification Modelscited by 43
  4. 2021Securing Secure Aggregation: Mitigating Multi-Round Privacy Leakage in Federated Learningcited by 39
  5. 2020Federated Transfer Learning for EEG Signal Classificationcited by 37
  6. 2022Split HE: Fast Secure Inference Combining Split Learning and Homomorphic Encryptioncited by 11
  7. 2025A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectivescited by 7
  8. 2022A Framework for Preserving Privacy and Cybersecurity in Brain-Computer Interfacing Applicationscited by 4
  9. 2023Toward Practical Privacy-Preserving Convolutional Neural Networks Exploiting Fully Homomorphic Encryptioncited by 4
  10. 2024Protecting Multiple Types of Privacy Simultaneously in EEG-based Brain-Computer Interfacescited by 3
  11. 2024PAT: Privacy-Preserving Adversarial Transfer for Accurate, Robust and Privacy-Preserving EEG Decodingcited by 3
  12. 2026SAFE: Secure and Accurate Federated Learning for Privacy-Preserving Brain-Computer Interfacescited by 2
2 more
  1. 2022Cancellable Template Design for Privacy-Preserving EEG Biometric Authentication Systemscited by 1
  2. 2025Protecting Intellectual Property of EEG-based Neural Networks with Watermarkingcited by 1

Built on by

Not cited yet.