Differentially Private Conformal Prediction

2026-04-16

AI Summary

This work addresses the inefficiency of existing conformal prediction methods under differential privacy constraints, which typically rely on data splitting and thereby sacrifice statistical efficiency. The authors propose Differentially Private Conformal Prediction (DPCP), the first framework to integrate differential privacy with split-free conformal prediction. DPCP employs a private quantile calibration mechanism to enable end-to-end differentially private uncertainty quantification. Theoretically, DPCP is proven to satisfy differential privacy while maintaining valid coverage guarantees, and it yields substantially tighter prediction sets than prior private split-based approaches under the same privacy budget. Empirical evaluations on both synthetic and real-world datasets demonstrate that DPCP significantly outperforms existing differentially private conformal methods, achieving higher predictive efficiency without compromising privacy protection.

Technology Category

• Machine Learning: Privacy
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Computer Vision: Bias, Fairness & Privacy

Application Category

• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Conformal prediction (CP) has attracted broad attention as a simple and flexible framework for uncertainty quantification through prediction sets. In this work, we study how to deploy CP under differential privacy (DP) in a statistically efficient manner. We first introduce differential CP, a non-splitting conformal procedure that avoids the efficiency loss caused by data splitting and serves as a bridge between oracle CP and private conformal inference. By exploiting the stability properties of DP mechanisms, differential CP establishes a direct connection to oracle CP and inherits corresponding validity behavior. Building on this idea, we develop Differentially Private Conformal Prediction (DPCP), a fully private procedure that combines DP model training with a private quantile mechanism for calibration. We establish the end-to-end privacy guarantee of DPCP and investigate its coverage properties under additional regularity conditions. We further study the efficiency of both differential CP and DPCP under empirical risk minimization and general regression models, showing that DPCP can produce tighter prediction sets than existing private split conformal approaches under the same privacy budget. Numerical experiments on synthetic and real datasets demonstrate the practical effectiveness of the proposed methods.

Problem

• Differential Privacy
• Conformal Prediction
• Uncertainty Quantification
• Prediction Sets
• Privacy-Preserving Inference

Innovation

• Differentially Private Conformal Prediction
• differential CP
• private quantile mechanism
• data splitting avoidance
• prediction set efficiency