# PRICURE: Privacy-Preserving Collaborative Inference in a Multi-Party Setting

arXiv: https://arxiv.org/abs/2102.09751 · HTML: https://mlsanity.com/paper/2102.09751/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Membership inference attacks, one of 12 directions in LLM safety and security.
- Builds on 13 of its 43 references that are in the map.
- First posted on arXiv 19 Feb 2021.

## Placed in

- LLM safety and security / [Membership inference attacks](https://mlsanity.com/safety/membership-inference-attacks/)

## Builds on (most cited first, 13 of 13)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Stealing Machine Learning Models via Prediction APIs](https://mlsanity.com/paper/1609.02943/) (2016)
- [Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data](https://mlsanity.com/paper/1610.05755/) (2016)
- [Scalable Private Learning with PATE](https://mlsanity.com/paper/1802.08908/) (2018)
- [Deep Reinforcement Learning framework for Autonomous Driving](https://mlsanity.com/paper/1704.02532/) (2017)
- [Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applications](https://mlsanity.com/paper/1801.03239/) (2018)
- [An Overview of Privacy in Machine Learning](https://mlsanity.com/paper/2005.08679/) (2020)
- [Privacy-Preserving Collaborative Prediction using Random Forests](https://mlsanity.com/paper/1811.08695/) (2018)
- [An Improved E-voting scheme using Secret Sharing based Secure Multi-party Computation](https://mlsanity.com/paper/1502.07469/) (2015)
- [Computer-aided proofs for multiparty computation with active security](https://mlsanity.com/paper/1806.07197/) (2018)
- [A New Approach to Privacy-Preserving Clinical Decision Support Systems](https://mlsanity.com/paper/1810.01107/) (2018)

## Built on by (most cited first, 9 of 9)

- [A Survey on Collaborative DNN Inference for Edge Intelligence](https://mlsanity.com/paper/2207.07812/) (2022)
- [DP-UTIL: Comprehensive Utility Analysis of Differential Privacy in Machine Learning](https://mlsanity.com/paper/2112.12998/) (2021)
- [MIAShield: Defending Membership Inference Attacks via Preemptive Exclusion of Members](https://mlsanity.com/paper/2203.00915/) (2022)
- [Attribute Inference Attacks in Online Multiplayer Video Games: a Case Study on Dota2](https://mlsanity.com/paper/2210.09028/) (2022)
- [Privacy-preserving machine learning for healthcare: open challenges and future perspectives](https://mlsanity.com/paper/2303.15563/) (2023)
- [Roulette: A Semantic Privacy-Preserving Device-Edge Collaborative Inference Framework for Deep Learning Classification Tasks](https://mlsanity.com/paper/2309.02820/) (2023)
- [Federated Inference: Toward Privacy-Preserving Collaborative and Incentivized Model Serving](https://mlsanity.com/paper/2603.02214/) (2026)
- [Beyond Classification: Task-Dependent Learnability under Privacy-Motivated Image Transformations](https://mlsanity.com/paper/2608.27066/) (2026)
- [Position Matters: Feature Inversion Attacks in ViT Split Inference with Token Reduction and Shuffling](https://mlsanity.com/paper/2609.01232/) (2026)

## Abstract (arXiv)

When multiple parties that deal with private data aim for a collaborative prediction task such as medical image classification, they are often constrained by data protection regulations and lack of trust among collaborating parties. If done in a privacy-preserving manner, predictive analytics can benefit from the collective prediction capability of multiple parties holding complementary datasets on the same machine learning task. This paper presents PRICURE, a system that combines complementary strengths of secure multi-party computation (SMPC) and differential privacy (DP) to enable privacy-preserving collaborative prediction among multiple model owners. SMPC enables secret-sharing of private models and client inputs with non-colluding secure servers to compute predictions without leaking model parameters and inputs. DP masks true prediction results via noisy aggregation so as to deter a semi-honest client who may mount membership inference attacks. We evaluate PRICURE on neural networks across four datasets including benchmark medical image classification datasets. Our results suggest PRICURE guarantees privacy for tens of model owners and clients with acceptable accuracy loss. We also show that DP reduces membership inference attack exposure without hurting accuracy.