Split Happens: Combating Advanced Threats with Split Learning and Function Secret Sharing
Not on the map. Why?
Abstract (arXiv)
Split Learning (SL) -- splits a model into two distinct parts to help protect client data while enhancing Machine Learning (ML) processes. Though promising, SL has proven vulnerable to different attacks, thus raising concerns about how effective it may be in terms of data privacy. Recent works have shown promising results for securing SL through the use of a novel paradigm, named Function Secret Sharing (FSS), in which servers obtain shares of a function they compute and operate on a public input hidden with a random mask. However, these works fall short in addressing the rising number of attacks which exist on SL. In SplitHappens, we expand the combination of FSS and SL to U-shaped SL. Similarly to other works, we are able to make use of the benefits of SL by reducing the communication and computational costs of FSS. However, a U-shaped SL provides a higher security guarantee than previous works, allowing a client to keep the labels of the training data secret, without having to share them with the server. Through this, we are able to generalize the security analysis of previous works and expand it to different attack vectors, such as modern model inversion attacks as well as label inference attacks. We tested our approach for two different convolutional neural networks on different datasets. These experiments show the effectiveness of our approach in reducing the training time as well as the communication costs when compared to simply using FSS while matching prior accuracy.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 18 of its 32 references that are in the map. First posted on arXiv 14 Jul 2025.
Builds on
18 of 32 references.
References · 18
- 2018Distributed learning of deep neural network over multiple agentscited by 279
- 2020Unleashing the Tiger: Inference Attacks on Split Learningcited by 105
- 2020FALCON: Honest-Majority Maliciously Secure Framework for Private Deep Learningcited by 74
- 2017CryptoDL: Deep Neural Networks over Encrypted Datacited by 56
- 2021UnSplit: Data-Oblivious Model Inversion, Model Stealing, and Label Inference Attacks Against Split Learningcited by 52
- 2020Can We Use Split Learning on 1D CNN Models for Privacy Preserving Training?cited by 50
- 2022ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learningcited by 36
- 2020POSEIDON: Privacy-Preserving Federated Neural Network Learningcited by 24
- 2020ARIANN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharingcited by 20
- 2024A Stealthy Wrongdoer: Feature-Oriented Reconstruction Attack against Split Learningcited by 17
- 2023Split Ways: Privacy-Preserving Training of Encrypted Data Using Split Learningcited by 15
- 2023Love or Hate? Share or Split? Privacy-Preserving Training Using Split Learning and Homomorphic Encryptioncited by 8
6 more
- 2024GuardML: Efficient Privacy-Preserving Machine Learning Services Through Hybrid Homomorphic Encryptioncited by 7
- 2023Split Without a Leak: Reducing Privacy Leakage in Split Learningcited by 6
- 2023Learning in the Dark: Privacy-Preserving Machine Learning using Function Approximationcited by 6
- 2024Make Split, not Hijack: Preventing Feature-Space Hijacking Attacks in Split Learningcited by 6
- 2023A More Secure Split: Enhancing the Security of Privacy-Preserving Split Learningcited by 5
- 2024A Pervasive, Efficient and Private Future: Realizing Privacy-Preserving Machine Learning Through Hybrid Homomorphic Encryptioncited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.