# Task-aware Privacy Preservation for Multi-dimensional Data

arXiv: https://arxiv.org/abs/2110.02329 · HTML: https://mlsanity.com/paper/2110.02329/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 63 references that are in the map.
- First posted on arXiv 5 Oct 2021.

## Builds on (most cited first, 24 of 24)

- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data](https://mlsanity.com/paper/1610.05755/) (2016)
- [RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response](https://mlsanity.com/paper/1407.6981/) (2014)
- [Subsampled R'enyi Differential Privacy and Analytical Moments Accountant](https://mlsanity.com/paper/1808.00087/) (2018)
- [Differentiable MPC for End-to-end Planning and Control](https://mlsanity.com/paper/1810.13400/) (2018)
- [Collecting Telemetry Data Privately](https://mlsanity.com/paper/1712.01524/) (2017)
- [Deep Learning with Gaussian Differential Privacy](https://mlsanity.com/paper/1911.11607/) (2019)
- [A General Approach to Adding Differential Privacy to Iterative Training Procedures](https://mlsanity.com/paper/1812.06210/) (2018)
- [Collecting and Analyzing Multidimensional Data with Local Differential Privacy](https://mlsanity.com/paper/1907.00782/) (2019)
- [Local Differential Privacy for Deep Learning](https://mlsanity.com/paper/1908.02997/) (2019)
- [FedSel: Federated SGD under Local Differential Privacy with Top-k Dimension Selection](https://mlsanity.com/paper/2003.10637/) (2020)
- [Adaptive Laplace Mechanism: Differential Privacy Preservation in Deep Learning](https://mlsanity.com/paper/1709.05750/) (2017)
- [Not Just Privacy: Improving Performance of Private Deep Learning in Mobile Cloud](https://mlsanity.com/paper/1809.03428/) (2018)
- [Differential Privacy Techniques for Cyber Physical Systems: A Survey](https://mlsanity.com/paper/1812.02282/) (2018)
- [Perceptual Indistinguishability-Net (PI-Net): Facial Image Obfuscation with Manipulable Semantics](https://mlsanity.com/paper/2104.01753/) (2021)
- [Context-Aware Local Differential Privacy](https://mlsanity.com/paper/1911.00038/) (2019)
- [Empirical Risk Minimization in the Non-interactive Local Model of Differential Privacy](https://mlsanity.com/paper/2011.05934/) (2020)
- [The Role of Interactivity in Local Differential Privacy](https://mlsanity.com/paper/1904.03564/) (2019)
- [Heterogeneous Gaussian Mechanism: Preserving Differential Privacy in Deep Learning with Provable Robustness](https://mlsanity.com/paper/1906.01444/) (2019)
- [Utility-Optimized Local Differential Privacy Mechanisms for Distribution Estimation](https://mlsanity.com/paper/1807.11317/) (2018)
- [Not All Features Are Equal: Discovering Essential Features for Preserving Prediction Privacy](https://mlsanity.com/paper/2003.12154/) (2020)
- [Data Sharing and Compression for Cooperative Networked Control](https://mlsanity.com/paper/2109.14675/) (2021)
- [Representation Learning for High-Dimensional Data Collection under Local Differential Privacy](https://mlsanity.com/paper/2010.12464/) (2020)

## Built on by (most cited first, 5 of 5)

- [Task-aware Distributed Source Coding under Dynamic Bandwidth](https://mlsanity.com/paper/2305.15523/) (2023)
- [Decouple-and-Sample: Protecting sensitive information in task agnostic data release](https://mlsanity.com/paper/2203.13204/) (2022)
- [A Path to Holistic Privacy in Stream Processing Systems](https://mlsanity.com/paper/2305.11638/) (2023)
- [Integrating Feature Correlation in Differential Privacy with Applications in DP-ERM](https://mlsanity.com/paper/2605.03945/) (2026)
- [Jacobian-Guided Anisotropic Noise Reshaping for Enhancing Representation Utility under Local Differential Privacy](https://mlsanity.com/paper/2605.16812/) (2026)

## Abstract (arXiv)

Local differential privacy (LDP) can be adopted to anonymize richer user data attributes that will be input to sophisticated machine learning (ML) tasks. However, today's LDP approaches are largely task-agnostic and often lead to severe performance loss -- they simply inject noise to all data attributes according to a given privacy budget, regardless of what features are most relevant for the ultimate task. In this paper, we address how to significantly improve the ultimate task performance with multi-dimensional user data by considering a task-aware privacy preservation problem. The key idea is to use an encoder-decoder framework to learn (and anonymize) a task-relevant latent representation of user data. We obtain an analytical near-optimal solution for the linear setting with mean-squared error (MSE) task loss. We also provide an approximate solution through a gradient-based learning algorithm for general nonlinear cases. Extensive experiments demonstrate that our task-aware approach significantly improves ultimate task accuracy compared to standard benchmark LDP approaches with the same level of privacy guarantee.