# Privacy-Preserving Conformal Prediction Under Local Differential Privacy

arXiv: https://arxiv.org/abs/2505.15721 · HTML: https://mlsanity.com/paper/2505.15721/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 29 references that are in the map.
- First posted on arXiv 21 May 2025.

## Builds on (most cited first, 17 of 17)

- [MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification](https://mlsanity.com/paper/2110.14795/) (2021)
- [Classification with Valid and Adaptive Coverage](https://mlsanity.com/paper/2006.02544/) (2020)
- [RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response](https://mlsanity.com/paper/1407.6981/) (2014)
- [MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis](https://mlsanity.com/paper/2010.14925/) (2020)
- [Deep Learning with Label Differential Privacy](https://mlsanity.com/paper/2102.06062/) (2021)
- [Fair Conformal Predictors for Applications in Medical Imaging](https://mlsanity.com/paper/2109.04392/) (2021)
- [Private Learning and Sanitization: Pure vs. Approximate Differential Privacy](https://mlsanity.com/paper/1407.2674/) (2014)
- [Discrete Distribution Estimation under Local Privacy](https://mlsanity.com/paper/1602.07387/) (2016)
- [Improving Trustworthiness of AI Disease Severity Rating in Medical Imaging with Ordinal Conformal Prediction Sets](https://mlsanity.com/paper/2207.02238/) (2022)
- [Practical Locally Private Heavy Hitters](https://mlsanity.com/paper/1707.04982/) (2017)
- [Adaptive conformal classification with noisy labels](https://mlsanity.com/paper/2309.05092/) (2023)
- [Private Prediction Sets](https://mlsanity.com/paper/2102.06202/) (2021)
- [Locally Private Mean Estimation: Z-test and Tight Confidence Intervals](https://mlsanity.com/paper/1810.08054/) (2018)
- [Differential Privacy in the Shuffle Model: A Survey of Separations](https://mlsanity.com/paper/2107.11839/) (2021)
- [A Conformal Prediction Score that is Robust to Label Noise](https://mlsanity.com/paper/2405.02648/) (2024)
- [Split Conformal Prediction under Data Contamination](https://mlsanity.com/paper/2407.07700/) (2024)
- [Conformal Prediction of Classifiers with Many Classes based on Noisy Labels](https://mlsanity.com/paper/2501.12749/) (2025)

## Built on by (most cited first, 2 of 2)

- [Extending Prediction-Powered Inference through Conformal Prediction](https://mlsanity.com/paper/2510.16166/) (2025)
- [Differentially Private Conformal Prediction via Quantile Binary Search](https://mlsanity.com/paper/2507.12497/) (2025)

## Abstract (arXiv)

Conformal prediction (CP) provides sets of candidate classes with a guaranteed probability of containing the true class. However, it typically relies on a calibration set with clean labels. We address privacy-sensitive scenarios where the aggregator is untrusted and can only access a perturbed version of the true labels. We propose two complementary approaches under local differential privacy (LDP). In the first approach, users do not access the model but instead provide their input features and a perturbed label using a k-ary randomized response. In the second approach, which enforces stricter privacy constraints, users add noise to their conformity score by binary search response. This method requires access to the classification model but preserves both data and label privacy. Both approaches compute the conformal threshold directly from noisy data without accessing the true labels. We prove finite-sample coverage guarantees and demonstrate robust coverage even under severe randomization. This approach unifies strong local privacy with predictive uncertainty control, making it well-suited for sensitive applications such as medical imaging or large language model queries, regardless of whether users can (or are willing to) compute their own scores.