A Taxonomy of Attacks and Defenses in Split Learning
Not on the map. Why?
Abstract (arXiv)
Split Learning (SL) has emerged as a promising paradigm for distributed deep learning, allowing resource-constrained clients to offload portions of their model computation to servers while maintaining collaborative learning. However, recent research has demonstrated that SL remains vulnerable to a range of privacy and security threats, including information leakage, model inversion, and adversarial attacks. While various defense mechanisms have been proposed, a systematic understanding of the attack landscape and corresponding countermeasures is still lacking. In this study, we present a comprehensive taxonomy of attacks and defenses in SL, categorizing them along three key dimensions: employed strategies, constraints, and effectiveness. Furthermore, we identify key open challenges and research gaps in SL based on our systematization, highlighting potential future directions.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 48 of its 88 references that are in the map. First posted on arXiv 9 May 2025.
Builds on
48 of 88 references.
References · 48
- 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
- 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
- 2018Federated Learning with Non-IID Datacited by 1,108
- 2019Deep Leakage from Gradientscited by 1,021
- 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
- 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 395
- 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 334
- 2020SplitFed: When Federated Learning Meets Split Learningcited by 310
- 2018Distributed learning of deep neural network over multiple agentscited by 279
- 2018Machine Learning with Membership Privacy using Adversarial Regularizationcited by 186
- 2020Unleashing the Tiger: Inference Attacks on Split Learningcited by 105
- 2021Label Leakage and Protection in Two-party Split Learningcited by 90
36 more
- 2019Split Learning for collaborative deep learning in healthcarecited by 73
- 2020NoPeek: Information leakage reduction to share activations in distributed deep learningcited by 66
- 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
- 2023Privacy Side Channels in Machine Learning Systemscited by 40
- 2022ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learningcited by 36
- 2021Practical Defences Against Model Inversion Attacks for Split Neural Networkscited by 29
- 2020DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networkscited by 23
- 2025A Survey of Zero-Knowledge Proof Based Verifiable Machine Learningcited by 22
- 2021SplitGuard: Detecting and Mitigating Training-Hijacking Attacks in Split Learningcited by 20
- 2024A Stealthy Wrongdoer: Feature-Oriented Reconstruction Attack against Split Learningcited by 17
- 2021ExPLoit: Extracting Private Labels in Split Learningcited by 15
- 2022Feature Space Hijacking Attacks against Differentially Private Split Learningcited by 15
- 2022Similarity-based Label Inference Attack against Training and Inference of Split Learningcited by 15
- 2023Split Ways: Privacy-Preserving Training of Encrypted Data Using Split Learningcited by 15
- 2023Bounding the Invertibility of Privacy-preserving Instance Encoding using Fisher Informationcited by 13
- 2023Passive Inference Attacks on Split Learning via Adversarial Regularizationcited by 9
- 2023Label Inference Attack against Split Learning under Regression Settingcited by 8
- 2023Secure Split Learning against Property Inference, Data Reconstruction, and Feature Space Hijacking Attackscited by 8
- 2023Love or Hate? Share or Split? Privacy-Preserving Training Using Split Learning and Homomorphic Encryptioncited by 8
- 2023Enhancing Accuracy-Privacy Trade-off in Differentially Private Split Learningcited by 8
- 2024A Fast, Performant, Secure Distributed Training Framework For Large Language Modelcited by 8
- 2022Get your Foes Fooled: Proximal Gradient Split Learning for Defense against Model Inversion Attacks on IoMT datacited by 7
- 2025SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)cited by 7
- 2023On Feasibility of Server-side Backdoor Attacks on Split Learningcited by 6
- 2023On the Robustness of Split Learning against Adversarial Attackscited by 6
- 2023Split Without a Leak: Reducing Privacy Leakage in Split Learningcited by 6
- 2024Make Split, not Hijack: Preventing Feature-Space Hijacking Attacks in Split Learningcited by 6
- 2023Split Learning for Distributed Collaborative Training of Deep Learning Models in Health Informaticscited by 5
- 2023A More Secure Split: Enhancing the Security of Privacy-Preserving Split Learningcited by 5
- 2022Split-U-Net: Preventing Data Leakage in Split Learning for Collaborative Multi-Modal Brain Tumor Segmentationcited by 4
- 2022Split Learning without Local Weight Sharing to Enhance Client-side Data Privacycited by 4
- 2023SplitOut: Out-of-the-Box Training-Hijacking Detection in Split Learning via Outlier Detectioncited by 4
- 2023Analyzing the vulnerabilities in SplitFed Learning: Assessing the robustness against Data Poisoning Attackscited by 4
- 2021SoK: Privacy-preserving Deep Learning with Homomorphic Encryptioncited by 3
- 2024Adaptive Differential Privacy in Federated Learning: A Priority-Based Approachcited by 3
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.