Privacy
Cross-source consensus on Privacy from 1 sources and 5 claims.
1 sources · 5 claims
How it works
Risks & contraindications
Evidence quality
Highlighted claims
- The privacy analysis uses empirical output perturbation rather than formal differential privacy. — Mixed-Precision Information Bottlenecks for On-Device Trait-State Disentanglement in Bipolar Agitation Detection
- The system does not provide formal epsilon-delta differential privacy because neural feature-extractor sensitivity is estimated empirically rather than tightly bounded. — Mixed-Precision Information Bottlenecks for On-Device Trait-State Disentanglement in Bipolar Agitation Detection
- During onboarding, Gaussian noise is added to trait embeddings with selected scale sigma 25.3 per dimension. — Mixed-Precision Information Bottlenecks for On-Device Trait-State Disentanglement in Bipolar Agitation Detection
- The paper describes privacy as empirical mitigation rather than a formal guarantee. — Mixed-Precision Information Bottlenecks for On-Device Trait-State Disentanglement in Bipolar Agitation Detection
- Adding noise with sigma 25.3 made MIA-AUC near random but reduced agitation prediction performance. — Mixed-Precision Information Bottlenecks for On-Device Trait-State Disentanglement in Bipolar Agitation Detection