Jaeho Jin

Pushing the (Decision) Boundaries: Dynamically Calibrating Differentially Private Noise to Explainability in Federated Learning

XCal-FL is proposed, a closed-loop, explainability-driven local training algorithm for image classification in cross-silo FL that dynamically calibrates DP noise from three complementary signals, suggesting explainability is a distinct dimension of the privacy trade-off that cannot be inferred from utility alone, with...