Tag: membership inference

A global data science competition showed synthetic cohorts can support post-transplant survival modeling, though equity gains attenuated under domain shift ...

A new study reveals that federated learning for EEG data remains vulnerable to privacy attacks, though differential privacy can significantly ...

Researchers have built an open-source Python library that scores synthetic EEG data across fidelity, diversity and privacy using interpretable, real-data-normalised ...

A federated, differentially private multimodal framework detects depression and anxiety across three benchmarks with F1 up to 0.806 while cutting ...

A Scientific Reports study presents a causal-enhanced federated transfer learning framework that improved cross-domain generalization robustness by 43% over conventional ...

A new flow matching framework assigns each tabular variable type its natural geometric space, improving synthetic data quality and resisting ...

A new safety audit shows that machine unlearning in medical AI can silently degrade performance on rare diagnoses, and proposes ...

Researchers have developed SURGE, a graph unlearning framework that treats data deletion requests as structural perturbations and repairs graph neural ...

Researchers have developed a hypernetwork-based framework that lets continually learning AI systems erase specific tasks without access to the original ...

A new systematic survey maps the full landscape of privacy attacks on deep learning and finds that while differential privacy ...