mlsanityData to 7 Oct 2026

Practical Defences Against Model Inversion Attacks for Split Neural Networks

arXiv 2104.05743 ↗First posted 12 Apr 2021cs.LG cs.CR cs.DCcited by 29

Not on the map. Why?

Abstract (arXiv)

We describe a threat model under which a split network-based federated learning system is susceptible to a model inversion attack by a malicious computational server. We demonstrate that the attack can be successfully performed with limited knowledge of the data distribution by the attacker. We propose a simple additive noise method to defend against model inversion, finding that the method can significantly reduce attack efficacy at an acceptable accuracy trade-off on MNIST. Furthermore, we show that NoPeekNN, an existing defensive method, protects different information from exposure, suggesting that a combined defence is necessary to fully protect private user data.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 24 of its 36 references that are in the map. First posted on arXiv 12 Apr 2021.

Builds on

24 of 36 references.

References · 24

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2016Deep Learning with Differential Privacycited by 2,682
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  5. 2020Extracting Training Data from Large Language Modelscited by 2,144
  6. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  7. 2019Towards Federated Learning at Scale: System Designcited by 826
  8. 2018How To Backdoor Federated Learningcited by 745
  9. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  10. 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 391
  11. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 347
  12. 2020FedML: A Research Library and Benchmark for Federated Machine Learningcited by 298
12 more
  1. 2018Scalable Private Learning with PATEcited by 266
  2. 2019The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networkscited by 241
  3. 2018Stealing Hyperparameters in Machine Learningcited by 115
  4. 2018A generic framework for privacy preserving deep learningcited by 103
  5. 2020Can We Use Split Learning on 1D CNN Models for Privacy Preserving Training?cited by 50
  6. 2020SplitNN-driven Vertical Partitioningcited by 42
  7. 2021PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNNcited by 35
  8. 2018No Peek: A Survey of private distributed deep learningcited by 30
  9. 2021Privacy and Trust Redefined in Federated Machine Learningcited by 13
  10. 2020Asymmetric Private Set Intersection with Applications to Contact Tracing and Private Vertical Federated Machine Learningcited by 12
  11. 2020Evaluation of Inference Attack Models for Deep Learning on Medical Datacited by 9
  12. 2020A Distributed Trust Framework for Privacy-Preserving Machine Learningcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 5; 2023: 5; 2024: 6; 2025: 7; 2026: 3.

29 papers.

Sort:

By area:

  1. 2021Survey: Leakage and Privacy at Inference Timecited by 44
  2. 2022ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learningcited by 36
  3. 2024Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defensescited by 30
  4. 2021ExPLoit: Extracting Private Labels in Split Learningcited by 15
  5. 2022Combined Federated and Split Learning in Edge Computing for Ubiquitous Intelligence in Internet of Things: State of the Art and Future Directionscited by 14
  6. 2023Bounding the Invertibility of Privacy-preserving Instance Encoding using Fisher Informationcited by 11
  7. 2021Privacy Vulnerability of Split Computing to Data-Free Model Inversion Attackscited by 8
  8. 2024Improving Robustness to Model Inversion Attacks via Sparse Coding Architecturescited by 8
  9. 2022Get your Foes Fooled: Proximal Gradient Split Learning for Defense against Model Inversion Attacks on IoMT datacited by 7
  10. 2023Split Without a Leak: Reducing Privacy Leakage in Split Learningcited by 6
  11. 2025Theoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference Systemscited by 6
  12. 2024A Hybrid Quantum Neural Network for Split Learningcited by 5
17 more
  1. 2024MIBench: A Comprehensive Framework for Benchmarking Model Inversion Attack and Defensecited by 5
  2. 2023Analyzing the vulnerabilities in SplitFed Learning: Assessing the robustness against Data Poisoning Attackscited by 4
  3. 2024SFPrompt: Communication-Efficient Split Federated Fine-Tuning for Large Pre-Trained Models over Resource-Limited Devicescited by 4
  4. 2022Measuring and Controlling Split Layer Privacy Leakage Using Fisher Informationcited by 3
  5. 2025DRAG: Data Reconstruction Attack using Guided Diffusioncited by 3
  6. 2023Approximating ReLU on a Reduced Ring for Efficient MPC-based Private Inferencecited by 2
  7. 2025P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devicescited by 2
  8. 2025What Your Features Reveal: Data-Efficient Black-Box Feature Inversion Attack for Split DNNscited by 2
  9. 2025A Taxonomy of Attacks and Defenses in Split Learningcited by 1
  10. 2025Oops!... They Stole it Again: Attacks on Split Learningcited by 1
  11. 2026Privacy-Preserving Split Learning for Federated LLM Fine-Tuningcited by 1
  12. 2022Split Federated Learning on Micro-controllers: A Keyword Spotting Showcasecited by 0
  13. 2023GAN-based Vertical Federated Learning for Label Protection in Binary Classificationcited by 0
  14. 2024Enhancing Privacy in ControlNet and Stable Diffusion via Split Learningcited by 0
  15. 2025Revisiting the Privacy Risks of Split Inference: A GAN-Based Data Reconstruction Attack via Progressive Feature Optimizationcited by 0
  16. 2026A Privacy Study of Sparse Collaborative Inferencecited by 0
  17. 2026Spectrum-Aware Bounds on Invertibility for Privacy-Enhancing Instance Encodingcited by 0