# Towards Privacy-Preserving Split Learning: Destabilizing Adversarial Inference and Reconstruction Attacks in the Cloud

arXiv: https://arxiv.org/abs/2502.20629 · HTML: https://mlsanity.com/paper/2502.20629/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Feb 2025.

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

- [Verifiable Split Learning via zk-SNARKs](https://mlsanity.com/paper/2511.01356/) (2025)
- [Keyed Nonlinear Transform: Lightweight Privacy-Enhancing Feature Sharing for Medical Image Analysis](https://mlsanity.com/paper/2605.14123/) (2026)

## Abstract (arXiv)

This work aims to provide both privacy and utility within a split learning framework while considering both forward attribute inference and backward reconstruction attacks. To address this, a novel approach has been proposed, which makes use of class activation maps and autoencoders as a plug-in strategy aiming to increase the user's privacy and destabilize an adversary. The proposed approach is compared with a dimensionality-reduction-based plug-in strategy, which makes use of principal component analysis to transform the feature map onto a lower-dimensional feature space. Our work shows that our proposed autoencoder-based approach is preferred as it can provide protection at an earlier split position over the tested architectures in our setting, and, hence, better utility for resource-constrained devices in edge-cloud collaborative inference (EC) systems.