# PriMask: Cascadable and Collusion-Resilient Data Masking for Mobile Cloud Inference

arXiv: https://arxiv.org/abs/2211.06716 · HTML: https://mlsanity.com/paper/2211.06716/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 75 references that are in the map.
- First posted on arXiv 12 Nov 2022.

## Builds on (most cited first, 30 of 31)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Federated Learning with Differential Privacy: Algorithms and Performance Analysis](https://mlsanity.com/paper/1911.00222/) (2019)
- [Split learning for health: Distributed deep learning without sharing raw patient data](https://mlsanity.com/paper/1812.00564/) (2018)
- [A Survey of Privacy Attacks in Machine Learning](https://mlsanity.com/paper/2007.07646/) (2020)
- [Thieves on Sesame Street! Model Extraction of BERT-based APIs](https://mlsanity.com/paper/1910.12366/) (2019)
- [Unleashing the Tiger: Inference Attacks on Split Learning](https://mlsanity.com/paper/2012.02670/) (2020)
- [MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation](https://mlsanity.com/paper/2005.03161/) (2020)
- [PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments](https://mlsanity.com/paper/2104.14380/) (2021)
- [Overlearning Reveals Sensitive Attributes](https://mlsanity.com/paper/1905.11742/) (2019)
- [AI Benchmark: Running Deep Neural Networks on Android Smartphones](https://mlsanity.com/paper/1810.01109/) (2018)
- [Mobile Sensor Data Anonymization](https://mlsanity.com/paper/1810.11546/) (2018)
- [UnSplit: Data-Oblivious Model Inversion, Model Stealing, and Label Inference Attacks Against Split Learning](https://mlsanity.com/paper/2108.09033/) (2021)
- [HyperGAN: A Generative Model for Diverse, Performant Neural Networks](https://mlsanity.com/paper/1901.11058/) (2019)
- [Can We Use Split Learning on 1D CNN Models for Privacy Preserving Training?](https://mlsanity.com/paper/2003.12365/) (2020)
- [Multi-Loss Weighting with Coefficient of Variations](https://mlsanity.com/paper/2009.01717/) (2020)
- [MEGEX: Data-Free Model Extraction Attack against Gradient-Based Explainable AI](https://mlsanity.com/paper/2107.08909/) (2021)
- [A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics](https://mlsanity.com/paper/1703.02952/) (2017)
- [Not Just Privacy: Improving Performance of Private Deep Learning in Mobile Cloud](https://mlsanity.com/paper/1809.03428/) (2018)
- [Adversarial Distillation of Bayesian Neural Network Posteriors](https://mlsanity.com/paper/1806.10317/) (2018)
- [DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networks](https://mlsanity.com/paper/2012.11025/) (2020)
- [Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputs](https://mlsanity.com/paper/2105.12049/) (2021)
- [TIPRDC: Task-Independent Privacy-Respecting Data Crowdsourcing Framework for Deep Learning with Anonymized Intermediate Representations](https://mlsanity.com/paper/2005.11480/) (2020)
- [DeepObfuscator: Obfuscating Intermediate Representations with Privacy-Preserving Adversarial Learning on Smartphones](https://mlsanity.com/paper/1909.04126/) (2019)
- [FastDeepIoT: Towards Understanding and Optimizing Neural Network Execution Time on Mobile and Embedded Devices](https://mlsanity.com/paper/1809.06970/) (2018)
- [Privacy Partitioning: Protecting User Data During the Deep Learning Inference Phase](https://mlsanity.com/paper/1812.02863/) (2018)
- [SCOTCH: An Efficient Secure Computation Framework for Secure Aggregation](https://mlsanity.com/paper/2201.07730/) (2022)
- [On Lightweight Privacy-Preserving Collaborative Learning for IoT Objects](https://mlsanity.com/paper/1902.05197/) (2019)
- [Lightweight and Unobtrusive Data Obfuscation at IoT Edge for Remote Inference](https://mlsanity.com/paper/1912.09859/) (2019)

## Built on by (most cited first, 3 of 3)

- [SwapNet: Efficient Swapping for DNN Inference on Edge AI Devices Beyond the Memory Budget](https://mlsanity.com/paper/2401.16757/) (2024)
- [SVDefense: Effective Defense against Gradient Inversion Attacks via Singular Value Decomposition](https://mlsanity.com/paper/2510.03319/) (2025)
- [Cloak of Invisibility: Real-Time Privacy-Preserving Volumetric Video Streaming](https://mlsanity.com/paper/2608.11645/) (2026)

## Abstract (arXiv)

Mobile cloud offloading is indispensable for inference tasks based on large-scale deep models. However, transmitting privacy-rich inference data to the cloud incurs concerns. This paper presents the design of a system called PriMask, in which the mobile device uses a secret small-scale neural network called MaskNet to mask the data before transmission. PriMask significantly weakens the cloud's capability to recover the data or extract certain private attributes. The MaskNet is em cascadable in that the mobile can opt in to or out of its use seamlessly without any modifications to the cloud's inference service. Moreover, the mobiles use different MaskNets, such that the collusion between the cloud and some mobiles does not weaken the protection for other mobiles. We devise a em split adversarial learning method to train a neural network that generates a new MaskNet quickly (within two seconds) at run time. We apply PriMask to three mobile sensing applications with diverse modalities and complexities, i.e., human activity recognition, urban environment crowdsensing, and driver behavior recognition. Results show PriMask's effectiveness in all three applications.