# Privacy-Preserving Feature Selection with Secure Multiparty Computation

arXiv: https://arxiv.org/abs/2102.03517 · HTML: https://mlsanity.com/paper/2102.03517/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 36 references that are in the map.
- First posted on arXiv 6 Feb 2021.

## Builds on (most cited first, 9 of 9)

- [Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applications](https://mlsanity.com/paper/1801.03239/) (2018)
- [CrypTFlow: Secure TensorFlow Inference](https://mlsanity.com/paper/1909.07814/) (2019)
- [QUOTIENT: Two-Party Secure Neural Network Training and Prediction](https://mlsanity.com/paper/1907.03372/) (2019)
- [Secure Evaluation of Quantized Neural Networks](https://mlsanity.com/paper/1910.12435/) (2019)
- [Protecting Privacy of Users in Brain-Computer Interface Applications](https://mlsanity.com/paper/1907.01586/) (2019)
- [High Performance Logistic Regression for Privacy-Preserving Genome Analysis](https://mlsanity.com/paper/2002.05377/) (2020)
- [Secure multiparty computations in floating-point arithmetic](https://mlsanity.com/paper/2001.03192/) (2020)
- [Zig-zag Sort: A Simple Deterministic Data-Oblivious Sorting Algorithm Running in O(n log n) Time](https://mlsanity.com/paper/1403.2777/) (2014)
- [Secure Two-Party Feature Selection](https://mlsanity.com/paper/1901.00832/) (2019)

## Built on by (most cited first, 12 of 12)

- [Advances and Open Challenges in Federated Foundation Models](https://mlsanity.com/paper/2404.15381/) (2024)
- [FedSDG-FS: Efficient and Secure Feature Selection for Vertical Federated Learning](https://mlsanity.com/paper/2302.10417/) (2023)
- [Towards Interpretable Federated Learning](https://mlsanity.com/paper/2302.13473/) (2023)
- [Comet: Accelerating Private Inference for Large Language Model by Predicting Activation Sparsity](https://mlsanity.com/paper/2505.07239/) (2025)
- [Training Differentially Private Models with Secure Multiparty Computation](https://mlsanity.com/paper/2202.02625/) (2022)
- [Effect of Homomorphic Encryption on the Performance of Training Federated Learning Generative Adversarial Networks](https://mlsanity.com/paper/2207.00263/) (2022)
- [Blinder: End-to-end Privacy Protection in Sensing Systems via Personalized Federated Learning](https://mlsanity.com/paper/2209.12046/) (2022)
- [FedST: Secure Federated Shapelet Transformation for Time Series Classification](https://mlsanity.com/paper/2302.10631/) (2023)
- [Privacy Protectability: An Information-theoretical Approach](https://mlsanity.com/paper/2305.15697/) (2023)
- [Round and Communication Balanced Protocols for Oblivious Evaluation of Finite State Machines](https://mlsanity.com/paper/2103.11240/) (2021)
- [Outsourced Privacy-Preserving Feature Selection Based on Fully Homomorphic Encryption](https://mlsanity.com/paper/2505.12869/) (2025)
- [Privacy-Preserving Feature Valuation in Vertical Federated Learning Using Shapley-CMI and PSI Permutation](https://mlsanity.com/paper/2512.14767/) (2025)

## Abstract (arXiv)

Existing work on privacy-preserving machine learning with Secure Multiparty Computation (MPC) is almost exclusively focused on model training and on inference with trained models, thereby overlooking the important data pre-processing stage. In this work, we propose the first MPC based protocol for private feature selection based on the filter method, which is independent of model training, and can be used in combination with any MPC protocol to rank features. We propose an efficient feature scoring protocol based on Gini impurity to this end. To demonstrate the feasibility of our approach for practical data science, we perform experiments with the proposed MPC protocols for feature selection in a commonly used machine-learning-as-a-service configuration where computations are outsourced to multiple servers, with semi-honest and with malicious adversaries. Regarding effectiveness, we show that secure feature selection with the proposed protocols improves the accuracy of classifiers on a variety of real-world data sets, without leaking information about the feature values or even which features were selected. Regarding efficiency, we document runtimes ranging from several seconds to an hour for our protocols to finish, depending on the size of the data set and the security settings.