Pretrained, Frozen, Still Leaking: Auditing Cross-Encoder Attribute Transfer in EEG Foundation Models
Researchers have developed a new auditing framework for EEG foundation models that goes beyond single-endpoint evaluations. This framework jointly audits multiple endpoints, revealing that models cleared by individual tests can still leak spectral attributes. A key finding is that a cross-encoder transfer audit demonstrates attribute leakage between different frozen encoders, even with standard defenses like DP-SGD failing to prevent it. AI
IMPACT This research introduces a more robust auditing framework for AI models, potentially leading to improved data privacy and security in foundation models.