Ethical Fairness without Demographics in Human-Centered AI

Researchers introduce Flare, a new AI fairness framework that ensures ethical outcomes without requiring demographic data, addressing privacy and regulatory concerns in human-centered AI applications. The system uses Fisher Information to detect hidden biases and includes a novel evaluation metric suite called BHE for measuring ethical fairness beyond traditional statistical measures.

• →Flare framework enables ethical AI fairness without accessing demographic or sensitive personal data.
• →The system uses Fisher Information geometry to uncover hidden performance disparities across population subgroups.
• →New BHE metric suite measures ethical fairness beyond conventional statistical parity approaches.
• →Framework addresses regulatory and privacy constraints that limit traditional fairness approaches.
• →Testing across physiological, behavioral, and clinical datasets shows improved ethical outcomes compared to existing methods.