mlsanityData to 14 Oct 2026

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

arXiv 2211.06716 ↗First posted 12 Nov 2022cs.CR cs.DC cs.LGcited by 3

Not on the map. Why?

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.

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

31 of 75 references.

References · 31

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,254
  3. 2016HyperNetworkscited by 1,027
  4. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
  5. 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 395
  6. 2020A Survey of Privacy Attacks in Machine Learningcited by 146
  7. 2019Thieves on Sesame Street! Model Extraction of BERT-based APIscited by 139
  8. 2020Unleashing the Tiger: Inference Attacks on Split Learningcited by 105
  9. 2020MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimationcited by 99
  10. 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
  11. 2019Overlearning Reveals Sensitive Attributescited by 76
  12. 2018AI Benchmark: Running Deep Neural Networks on Android Smartphonescited by 75
19 more
  1. 2018Mobile Sensor Data Anonymizationcited by 70
  2. 2021UnSplit: Data-Oblivious Model Inversion, Model Stealing, and Label Inference Attacks Against Split Learningcited by 52
  3. 2019HyperGAN: A Generative Model for Diverse, Performant Neural Networkscited by 51
  4. 2020Can We Use Split Learning on 1D CNN Models for Privacy Preserving Training?cited by 50
  5. 2020Multi-Loss Weighting with Coefficient of Variationscited by 36
  6. 2021MEGEX: Data-Free Model Extraction Attack against Gradient-Based Explainable AIcited by 35
  7. 2017A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analyticscited by 30
  8. 2018Not Just Privacy: Improving Performance of Private Deep Learning in Mobile Cloudcited by 28
  9. 2018Adversarial Distillation of Bayesian Neural Network Posteriorscited by 27
  10. 2020DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networkscited by 23
  11. 2021Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputscited by 18
  12. 2020TIPRDC: Task-Independent Privacy-Respecting Data Crowdsourcing Framework for Deep Learning with Anonymized Intermediate Representationscited by 17
  13. 2019DeepObfuscator: Obfuscating Intermediate Representations with Privacy-Preserving Adversarial Learning on Smartphonescited by 15
  14. 2018FastDeepIoT: Towards Understanding and Optimizing Neural Network Execution Time on Mobile and Embedded Devicescited by 14
  15. 2018Privacy Partitioning: Protecting User Data During the Deep Learning Inference Phasecited by 9
  16. 2022SCOTCH: An Efficient Secure Computation Framework for Secure Aggregationcited by 4
  17. 2019On Lightweight Privacy-Preserving Collaborative Learning for IoT Objectscited by 3
  18. 2019Lightweight and Unobtrusive Data Obfuscation at IoT Edge for Remote Inferencecited by 3
  19. 2015Crowd-ML: A Privacy-Preserving Learning Framework for a Crowd of Smart Devicescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 1.

3 papers.

  1. 2024SwapNet: Efficient Swapping for DNN Inference on Edge AI Devices Beyond the Memory Budgetcited by 3
  2. 2025SVDefense: Effective Defense against Gradient Inversion Attacks via Singular Value Decompositioncited by 2
  3. 2026Cloak of Invisibility: Real-Time Privacy-Preserving Volumetric Video Streamingcited by 0