mlsanityData to 7 Oct 2026

NoPeek: Information leakage reduction to share activations in distributed deep learning

arXiv 2008.09161 ↗First posted 20 Aug 2020cs.LG cs.DC stat.MLcited by 66

Not on the map. Why?

Abstract (arXiv)

For distributed machine learning with sensitive data, we demonstrate how minimizing distance correlation between raw data and intermediary representations reduces leakage of sensitive raw data patterns across client communications while maintaining model accuracy. Leakage (measured using distance correlation between input and intermediate representations) is the risk associated with the invertibility of raw data from intermediary representations. This can prevent client entities that hold sensitive data from using distributed deep learning services. We demonstrate that our method is resilient to such reconstruction attacks and is based on reduction of distance correlation between raw data and learned representations during training and inference with image datasets. We prevent such reconstruction of raw data while maintaining information required to sustain good classification accuracies.

Key facts. Cited by 66 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 12; 2023: 13; 2024: 12; 2025: 12; 2026: 11.

66 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. 2023Privacy and Efficiency of Communications in Federated Split Learningcited by 20
  4. 2021Revealing and Protecting Labels in Distributed Trainingcited by 17
  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. 2021Communication and Computation Reduction for Split Learning using Asynchronous Trainingcited by 11
  7. 2022Binarizing Split Learning for Data Privacy Enhancement and Computation Reductioncited by 11
  8. 2023Bounding the Invertibility of Privacy-preserving Instance Encoding using Fisher Informationcited by 11
  9. 2021A Coupled Design of Exploiting Record Similarity for Practical Vertical Federated Learningcited by 10
  10. 2022HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learningcited by 10
  11. 2022Split HE: Fast Secure Inference Combining Split Learning and Homomorphic Encryptioncited by 9
  12. 2023Passive Inference Attacks on Split Learning via Adversarial Regularizationcited by 9
38 more
  1. 2021AdaSplit: Adaptive Trade-offs for Resource-constrained Distributed Deep Learningcited by 8
  2. 2022Visual Transformer Meets CutMix for Improved Accuracy, Communication Efficiency, and Data Privacy in Split Learningcited by 8
  3. 2024Federated Transformer: Multi-Party Vertical Federated Learning on Practical Fuzzily Linked Datacited by 8
  4. 2024A Survey of Privacy Threats and Defense in Vertical Federated Learning: From Model Life Cycle Perspectivecited by 7
  5. 2025Towards Straggler-Resilient Split Federated Learning: An Unbalanced Update Approachcited by 7
  6. 2025Theoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference Systemscited by 6
  7. 2022LSTMSPLIT: Effective SPLIT Learning based LSTM on Sequential Time-Series Datacited by 5
  8. 2023Model Extraction Attacks on Split Federated Learningcited by 5
  9. 2023Input Reconstruction Attack against Vertical Federated Large Language Modelscited by 5
  10. 2024A Hybrid Quantum Neural Network for Split Learningcited by 5
  11. 2023SplitOut: Out-of-the-Box Training-Hijacking Detection in Split Learning via Outlier Detectioncited by 4
  12. 2023Analyzing the vulnerabilities in SplitFed Learning: Assessing the robustness against Data Poisoning Attackscited by 4
  13. 2024SFPrompt: Communication-Efficient Split Federated Fine-Tuning for Large Pre-Trained Models over Resource-Limited Devicescited by 4
  14. 2021Information Stealing in Federated Learning Systems Based on Generative Adversarial Networkscited by 3
  15. 2022Measuring and Controlling Split Layer Privacy Leakage Using Fisher Informationcited by 3
  16. 2022Protecting Split Learning by Potential Energy Losscited by 3
  17. 2022Scalable Collaborative Learning via Representation Sharingcited by 3
  18. 2023A Distance Correlation-Based Approach to Characterize the Effectiveness of Recurrent Neural Networks for Time Series Forecastingcited by 3
  19. 2023FLea: Addressing Data Scarcity and Label Skew in Federated Learning via Privacy-preserving Feature Augmentationcited by 3
  20. 2023Speed Up Federated Learning in Heterogeneous Environment: A Dynamic Tiering Approachcited by 3
  21. 2024MP-SL: Multihop Parallel Split Learningcited by 3
  22. 2024URVFL: Undetectable Data Reconstruction Attack on Vertical Federated Learningcited by 3
  23. 2024GAS: Generative Activation-Aided Asynchronous Split Federated Learningcited by 3
  24. 2025From Risk to Resilience: Towards Assessing and Mitigating the Risk of Data Reconstruction Attacks in Federated Learningcited by 3
  25. 2022Assessing Privacy Risks from Feature Vector Reconstruction Attackscited by 2
  26. 2023Defending Label Inference Attacks in Split Learning under Regression Settingcited by 2
  27. 2023Approximating ReLU on a Reduced Ring for Efficient MPC-based Private Inferencecited by 2
  28. 2024Communication-Efficient Training Workload Balancing for Decentralized Multi-Agent Learningcited by 2
  29. 2024SCALA: Split Federated Learning with Concatenated Activations and Logit Adjustmentscited by 2
  30. 2024Edge-Only Universal Adversarial Attacks in Distributed Learningcited by 2
  31. 2025Residual Reweighted Conformal Prediction for Graph Neural Networkscited by 2
  32. 2025Learning Obfuscations Of LLM Embedding Sequences: Stained Glass Transformcited by 2
  33. 2025What Your Features Reveal: Data-Efficient Black-Box Feature Inversion Attack for Split DNNscited by 2
  34. 2022Privacy Safe Representation Learning via Frequency Filtering Encodercited by 1
  35. 2023Privacy Protectability: An Information-theoretical Approachcited by 1
  36. 2025A Taxonomy of Attacks and Defenses in Split Learningcited by 1
  37. 2026The Art of Mixology: Mixup-based Obfuscation for Privacy-Preserving Split Learning in Large Language Modelscited by 1
  38. 2026TL++: Accuracy and Privacy Preserving Traversal Learning for Distributed Intelligent Systemscited by 1

50 most cited of 66 All 66 (JSON)