# Context-Aware Local Differential Privacy

arXiv: https://arxiv.org/abs/1911.00038 · HTML: https://mlsanity.com/paper/1911.00038/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 2019.

## Built on by (most cited first, 18 of 18)

- [Deep Learning with Label Differential Privacy](https://mlsanity.com/paper/2102.06062/) (2021)
- [AirGapAgent: Protecting Privacy-Conscious Conversational Agents](https://mlsanity.com/paper/2405.05175/) (2024)
- [Optimal Federated Learning for Nonparametric Regression with Heterogeneous Distributed Differential Privacy Constraints](https://mlsanity.com/paper/2406.06755/) (2024)
- [PRISM: Privacy-Aware Routing for Adaptive Cloud-Edge LLM Inference via Semantic Sketch Collaboration](https://mlsanity.com/paper/2511.22788/) (2025)
- [Degree-Preserving Randomized Response for Graph Neural Networks under Local Differential Privacy](https://mlsanity.com/paper/2202.10209/) (2022)
- [NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human](https://mlsanity.com/paper/2406.03749/) (2024)
- [Federated Nonparametric Hypothesis Testing with Differential Privacy Constraints: Optimal Rates and Adaptive Tests](https://mlsanity.com/paper/2406.06749/) (2024)
- [Task-aware Privacy Preservation for Multi-dimensional Data](https://mlsanity.com/paper/2110.02329/) (2021)
- [FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Health](https://mlsanity.com/paper/2509.14275/) (2025)
- [Decouple-and-Sample: Protecting sensitive information in task agnostic data release](https://mlsanity.com/paper/2203.13204/) (2022)
- [Algorithms with More Granular Differential Privacy Guarantees](https://mlsanity.com/paper/2209.04053/) (2022)
- [Scalable Collaborative Learning via Representation Sharing](https://mlsanity.com/paper/2211.10943/) (2022)
- [Enhancing Feature-Specific Data Protection via Bayesian Coordinate Differential Privacy](https://mlsanity.com/paper/2410.18404/) (2024)
- [Non-Asymptotic Analysis of Online Local Private Learning with SGD](https://mlsanity.com/paper/2507.07041/) (2025)
- [RPWithPrior: Label Differential Privacy in Regression](https://mlsanity.com/paper/2601.22625/) (2026)
- [Feature-Aware Anisotropic Local Differential Privacy for Utility-Preserving Graph Representation Learning in Metal Additive Manufacturing](https://mlsanity.com/paper/2604.05077/) (2026)
- [Integrating Feature Correlation in Differential Privacy with Applications in DP-ERM](https://mlsanity.com/paper/2605.03945/) (2026)
- [P2Skill: Privacy Preserving Skill Distillation for Cloud-Local LLM Inference Systems](https://mlsanity.com/paper/2608.14094/) (2026)

## Abstract (arXiv)

Local differential privacy (LDP) is a strong notion of privacy for individual users that often comes at the expense of a significant drop in utility. The classical definition of LDP assumes that all elements in the data domain are equally sensitive. However, in many applications, some symbols are more sensitive than others. This work proposes a context-aware framework of local differential privacy that allows a privacy designer to incorporate the application's context into the privacy definition. For binary data domains, we provide a universally optimal privatization scheme and highlight its connections to Warner's randomized response (RR) and Mangat's improved response. Motivated by geolocation and web search applications, for k-ary data domains, we consider two special cases of context-aware LDP: block-structured LDP and high-low LDP. We study discrete distribution estimation and provide communication-efficient, sample-optimal schemes and information-theoretic lower bounds for both models. We show that using contextual information can require fewer samples than classical LDP to achieve the same accuracy.