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

arXiv: https://arxiv.org/abs/2306.07973 · HTML: https://mlsanity.com/paper/2306.07973/

## Key facts

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

## Builds on (most cited first, 14 of 14)

- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Inverting Gradients -- How easy is it to break privacy in federated learning?](https://mlsanity.com/paper/2003.14053/) (2020)
- [Exploiting Unintended Feature Leakage in Collaborative Learning](https://mlsanity.com/paper/1805.04049/) (2018)
- [iDLG: Improved Deep Leakage from Gradients](https://mlsanity.com/paper/2001.02610/) (2020)
- [See through Gradients: Image Batch Recovery via GradInversion](https://mlsanity.com/paper/2104.07586/) (2021)
- [CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information](https://mlsanity.com/paper/2006.12013/) (2020)
- [Deep Learning with Label Differential Privacy](https://mlsanity.com/paper/2102.06062/) (2021)
- [Feature Inference Attack on Model Predictions in Vertical Federated Learning](https://mlsanity.com/paper/2010.10152/) (2020)
- [Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective](https://mlsanity.com/paper/2012.06043/) (2020)
- [Label Leakage and Protection in Two-party Split Learning](https://mlsanity.com/paper/2102.08504/) (2021)
- [CAFE: Catastrophic Data Leakage in Vertical Federated Learning](https://mlsanity.com/paper/2110.15122/) (2021)
- [Improving Robustness to Model Inversion Attacks via Mutual Information Regularization](https://mlsanity.com/paper/2009.05241/) (2020)
- [Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edge](https://mlsanity.com/paper/1812.06426/) (2018)
- [Mutual Information Regularization for Vertical Federated Learning](https://mlsanity.com/paper/2301.01142/) (2023)

## Built on by (most cited first, 4 of 4)

- [Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Survey](https://mlsanity.com/paper/2505.01821/) (2025)
- [A Survey on Cloud-Edge-Terminal Collaborative Intelligence in AIoT Networks](https://mlsanity.com/paper/2508.18803/) (2025)
- [From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language Models](https://mlsanity.com/paper/2606.14210/) (2026)
- [VMask: Tunable Label Privacy Protection for Vertical Federated Learning via Layer Masking](https://mlsanity.com/paper/2507.14629/) (2025)

## 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.