mlsanityData to 7 Oct 2026

PrivaScissors: Enhance the Privacy of Collaborative Inference through the Lens of Mutual Information

arXiv 2306.07973 ↗First posted 17 May 2023cs.CR cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Edge-cloud collaborative inference empowers resource-limited IoT devices to support deep learning applications without disclosing their raw data to the cloud server, thus preserving privacy. Nevertheless, prior research has shown that collaborative inference still results in the exposure of data and predictions from edge devices. To enhance the privacy of collaborative inference, we introduce a defense strategy called PrivaScissors, which is designed to reduce the mutual information between a model's intermediate outcomes and the device's data and predictions. We evaluate PrivaScissors's performance on several datasets in the context of diverse attacks and offer a theoretical robustness guarantee.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 14 of its 24 references that are in the map. First posted on arXiv 17 May 2023.

Builds on

14 of 24 references.

References · 14

  1. 2019Deep Leakage from Gradientscited by 1,004
  2. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  3. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  4. 2020iDLG: Improved Deep Leakage from Gradientscited by 367
  5. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 320
  6. 2020CLUB: A Contrastive Log-ratio Upper Bound of Mutual Informationcited by 233
  7. 2021Deep Learning with Label Differential Privacycited by 113
  8. 2020Feature Inference Attack on Model Predictions in Vertical Federated Learningcited by 105
  9. 2020Provable Defense against Privacy Leakage in Federated Learning from Representation Perspectivecited by 94
  10. 2021Label Leakage and Protection in Two-party Split Learningcited by 87
  11. 2021CAFE: Catastrophic Data Leakage in Vertical Federated Learningcited by 76
  12. 2020Improving Robustness to Model Inversion Attacks via Mutual Information Regularizationcited by 49
2 more
  1. 2018Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edgecited by 20
  2. 2023Mutual Information Regularization for Vertical Federated Learningcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Surveycited by 13
  2. 2025A Survey on Cloud-Edge-Terminal Collaborative Intelligence in AIoT Networkscited by 3
  3. 2026From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language Modelscited by 1
  4. 2025VMask: Tunable Label Privacy Protection for Vertical Federated Learning via Layer Maskingcited by 0