# Certification for Differentially Private Prediction in Gradient-Based Training Source: [Certification for Differentially Private Prediction in Gradient-Based Training]() Collection index: [llms.txt]() Data updated: 2025-10-26T04:52:59.877Z Authors: Matthew Wicker, Philip Sosnin, Igor Shilov, Adrianna Janik, Mark N. M\\"uller, Yves-Alexandre de Montjoye, Adrian Weller, Calvin Tsay Published: 2024-06-19T10:47:00.000Z ## Abstract We study private prediction where differential privacy is achieved by adding noise to the outputs of a non-private model. Existing methods rely on noise proportional to the global sensitivity of the model, often resulting in sub-optimal privacy-utility trade-offs compared to private training. We introduce a novel approach for computing dataset-specific upper bounds on prediction sensitivity by leveraging convex relaxation and bound propagation techniques. By combining these bounds with the smooth sensitivity mechanism, we significantly improve the privacy analysis of private prediction compared to global sensitivity-based approaches. Experimental results across real-world datasets in medical image classification and natural language processing demonstrate that our sensitivity bounds are can be orders of magnitude tighter than global sensitivity. Our approach provides a strong basis for the development of novel privacy preserving technologies. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()