AI RESEARCH
Membership Inference Attacks Expose Participation Privacy in ECG Foundation Encoders
arXiv CS.LG
•
ArXi:2604.10424v1 Announce Type: new Foundation-style ECG encoders pretrained with self-supervised learning are increasingly reused across tasks, institutions, and deployment contexts, often through model-as-a-service interfaces that expose scalar scores or latent representations. While such reuse improves data efficiency and generalization, it raises a participation privacy concern: can an adversary infer whether a specific individual or cohort contributed ECG data to pre