mlsanityData to 7 Oct 2026

Analyzing the vulnerabilities in SplitFed Learning: Assessing the robustness against Data Poisoning Attacks

arXiv 2307.03197 ↗First posted 4 Jul 2023cs.LG cs.AIcited by 4

On the map: LLM safety and security → Federated unlearning and poisoning

Abstract (arXiv)

Distributed Collaborative Machine Learning (DCML) is a potential alternative to address the privacy concerns associated with centralized machine learning. The Split learning (SL) and Federated Learning (FL) are the two effective learning approaches in DCML. Recently there have been an increased interest on the hybrid of FL and SL known as the SplitFed Learning (SFL). This research is the earliest attempt to study, analyze and present the impact of data poisoning attacks in SFL. We propose three kinds of novel attack strategies namely untargeted, targeted and distance-based attacks for SFL. All the attacks strategies aim to degrade the performance of the DCML-based classifier. We test the proposed attack strategies for two different case studies on Electrocardiogram signal classification and automatic handwritten digit recognition. A series of attack experiments were conducted by varying the percentage of malicious clients and the choice of the model split layer between the clients and the server. The results after the comprehensive analysis of attack strategies clearly convey that untargeted and distance-based poisoning attacks have greater impacts in evading the classifier outcomes compared to targeted attacks in SFL

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 18 of its 31 references that are in the map. First posted on arXiv 4 Jul 2023.

Builds on

18 of 31 references.

References · 18

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  3. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  4. 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 391
  5. 2020SplitFed: When Federated Learning Meets Split Learningcited by 308
  6. 2018Distributed learning of deep neural network over multiple agentscited by 277
  7. 2020Threats to Federated Learning: A Surveycited by 171
  8. 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 116
  9. 2020Unleashing the Tiger: Inference Attacks on Split Learningcited by 104
  10. 2021Label Leakage and Protection in Two-party Split Learningcited by 87
  11. 2020NoPeek: Information leakage reduction to share activations in distributed deep learningcited by 66
  12. 2021UnSplit: Data-Oblivious Model Inversion, Model Stealing, and Label Inference Attacks Against Split Learningcited by 52
6 more
  1. 2020Advancements of federated learning towards privacy preservation: from federated learning to split learningcited by 34
  2. 2021Practical Defences Against Model Inversion Attacks for Split Neural Networkscited by 29
  3. 2021ML Attack Models: Adversarial Attacks and Data Poisoning Attackscited by 23
  4. 2022Combined Federated and Split Learning in Edge Computing for Ubiquitous Intelligence in Internet of Things: State of the Art and Future Directionscited by 14
  5. 2022Semi-Targeted Model Poisoning Attack on Federated Learning via Backward Error Analysiscited by 9
  6. 2021Robust and Privacy-Preserving Collaborative Learning: A Comprehensive Surveycited by 5

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 2.

4 papers.

  1. 2023MISA: Unveiling the Vulnerabilities in Split Federated Learningcited by 3
  2. 2024SoK: Security and Privacy Risks of Healthcare AIcited by 2
  3. 2025A Taxonomy of Attacks and Defenses in Split Learningcited by 1
  4. 2025Oops!... They Stole it Again: Attacks on Split Learningcited by 1