SW-ProxyCE: Zero-Query Adversarial Transfer from Public EEG Encoders to Private Downstream Models
Read the original on arXiv Machine Learning →The paper introduces SW-ProxyCE, a zero-query adversarial attack that exploits publicly released EEG foundation encoders to generate transferable adversarial examples for private downstream models. By using a small labeled reference set and shrinkage-whitened class prototypes, the method recovers task-level decision geometry without training a surrogate classifier. Experiments across three EEG tasks and multiple encoders show that SW-ProxyCE consistently outperforms task-agnostic attacks, demonstrating that the strong transferability of EEG foundation models does not guarantee adversarial robustness.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.