# SecureSplit: Mitigating Backdoor Attacks in Split Learning

arXiv: https://arxiv.org/abs/2601.14054 · HTML: https://mlsanity.com/paper/2601.14054/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 48 references that are in the map.
- First posted on arXiv 20 Jan 2026.

## Builds on (most cited first, 22 of 22)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Local Model Poisoning Attacks to Byzantine-Robust Federated Learning](https://mlsanity.com/paper/1911.11815/) (2019)
- [Split learning for health: Distributed deep learning without sharing raw patient data](https://mlsanity.com/paper/1812.00564/) (2018)
- [FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping](https://mlsanity.com/paper/2012.13995/) (2020)
- [SplitFed: When Federated Learning Meets Split Learning](https://mlsanity.com/paper/2004.12088/) (2020)
- [Adversarial Neuron Pruning Purifies Backdoored Deep Models](https://mlsanity.com/paper/2110.14430/) (2021)
- [fastai: A Layered API for Deep Learning](https://mlsanity.com/paper/2002.04688/) (2020)
- [Detailed comparison of communication efficiency of split learning and federated learning](https://mlsanity.com/paper/1909.09145/) (2019)
- [FederatedScope: A Flexible Federated Learning Platform for Heterogeneity](https://mlsanity.com/paper/2204.05011/) (2022)
- [Byzantine-Robust Decentralized Federated Learning](https://mlsanity.com/paper/2406.10416/) (2024)
- [BlindFL: Vertical Federated Machine Learning without Peeking into Your Data](https://mlsanity.com/paper/2206.07975/) (2022)
- [AFLGuard: Byzantine-robust Asynchronous Federated Learning](https://mlsanity.com/paper/2212.06325/) (2022)
- [Asymmetrical Vertical Federated Learning](https://mlsanity.com/paper/2004.07427/) (2020)
- [Do We Really Need to Design New Byzantine-robust Aggregation Rules?](https://mlsanity.com/paper/2501.17381/) (2025)
- [SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)](https://mlsanity.com/paper/2501.06650/) (2025)
- [Byzantine-Robust Federated Learning over Ring-All-Reduce Distributed Computing](https://mlsanity.com/paper/2501.17392/) (2025)
- [Poisoning Attacks and Defenses to Federated Unlearning](https://mlsanity.com/paper/2501.17396/) (2025)
- [Securing Distributed Network Digital Twin Systems Against Model Poisoning Attacks](https://mlsanity.com/paper/2407.01917/) (2024)
- [VFLIP: A Backdoor Defense for Vertical Federated Learning via Identification and Purification](https://mlsanity.com/paper/2408.15591/) (2024)
- [Toward Malicious Clients Detection in Federated Learning](https://mlsanity.com/paper/2505.09110/) (2025)

## Abstract (arXiv)

Split Learning (SL) offers a framework for collaborative model training that respects data privacy by allowing participants to share the same dataset while maintaining distinct feature sets. However, SL is susceptible to backdoor attacks, in which malicious clients subtly alter their embeddings to insert hidden triggers that compromise the final trained model. To address this vulnerability, we introduce SecureSplit, a defense mechanism tailored to SL. SecureSplit applies a dimensionality transformation strategy to accentuate subtle differences between benign and poisoned embeddings, facilitating their separation. With this enhanced distinction, we develop an adaptive filtering approach that uses a majority-based voting scheme to remove contaminated embeddings while preserving clean ones. Rigorous experiments across four datasets (CIFAR-10, MNIST, CINIC-10, and ImageNette), five backdoor attack scenarios, and seven alternative defenses confirm the effectiveness of SecureSplit under various challenging conditions.