# PRIVEE: Privacy-Preserving Vertical Federated Learning Against Feature Inference Attacks

arXiv: https://arxiv.org/abs/2512.12840 · HTML: https://mlsanity.com/paper/2512.12840/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 37 references that are in the map.
- First posted on arXiv 14 Dec 2025.

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

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models](https://mlsanity.com/paper/1806.01246/) (2018)
- [MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples](https://mlsanity.com/paper/1909.10594/) (2019)
- [Feature Inference Attack on Model Predictions in Vertical Federated Learning](https://mlsanity.com/paper/2010.10152/) (2020)
- [Vertical Federated Learning: Challenges, Methodologies and Experiments](https://mlsanity.com/paper/2202.04309/) (2022)
- [Diffprivlib: The IBM Differential Privacy Library](https://mlsanity.com/paper/1907.02444/) (2019)
- [Defending Model Inversion and Membership Inference Attacks via Prediction Purification](https://mlsanity.com/paper/2005.03915/) (2020)
- [One Parameter Defense -- Defending against Data Inference Attacks via Differential Privacy](https://mlsanity.com/paper/2203.06580/) (2022)
- [Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey](https://mlsanity.com/paper/2309.16398/) (2023)
- [Strengthening Order Preserving Encryption with Differential Privacy](https://mlsanity.com/paper/2009.05679/) (2020)
- [POPE: Partial Order Preserving Encoding](https://mlsanity.com/paper/1610.04025/) (2016)

## Abstract (arXiv)

Vertical Federated Learning (VFL) enables collaborative model training across organizations that share common user samples but hold disjoint feature spaces. Despite its potential, VFL is susceptible to feature inference attacks, in which adversarial parties exploit shared confidence scores (prediction probabilities) during inference to reconstruct private input features of other participants. To counter this threat, we propose PRIVEE (PRIvacy-preserving Vertical fEderated lEarning), a novel defense mechanism named after the French word priv'ee, meaning "private." PRIVEE obfuscates confidence scores while preserving critical properties such as relative ranking and inter-score distances. Rather than exposing raw scores, PRIVEE only shares transformed representations, mitigating risk of reconstruction attacks without degrading model prediction accuracy. Extensive experiments show that PRIVEE achieves up to a 30 times increase in reconstruction error (MSE) against feature inference attacks, compared to the strongest competing defense, while preserving full predictive performance against advanced feature inference attacks.