# Data Minimization at Inference Time

arXiv: https://arxiv.org/abs/2305.17593 · HTML: https://mlsanity.com/paper/2305.17593/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 34 references that are in the map.
- First posted on arXiv 27 May 2023.

## Builds on (most cited first, 8 of 8)

- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Differentially Private Generative Adversarial Network](https://mlsanity.com/paper/1802.06739/) (2018)
- [Improving model calibration with accuracy versus uncertainty optimization](https://mlsanity.com/paper/2012.07923/) (2020)
- [Towards the Science of Security and Privacy in Machine Learning](https://mlsanity.com/paper/1611.03814/) (2016)
- [Robust and Differentially Private Mean Estimation](https://mlsanity.com/paper/2102.09159/) (2021)
- [Active Feature Acquisition with Generative Surrogate Models](https://mlsanity.com/paper/2010.02433/) (2020)
- [Dynamic Measurement Scheduling for Event Forecasting using Deep RL](https://mlsanity.com/paper/1901.09699/) (2019)
- [Why Pay More When You Can Pay Less: A Joint Learning Framework for Active Feature Acquisition and Classification](https://mlsanity.com/paper/1709.05964/) (2017)

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

- [Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents](https://mlsanity.com/paper/2502.18509/) (2025)
- [Towards Regulatable AI Systems: Technical Gaps and Policy Opportunities](https://mlsanity.com/paper/2306.12609/) (2023)
- [SoK: Data Minimization in Machine Learning](https://mlsanity.com/paper/2508.10836/) (2025)
- [Metanetworks as Regulatory Operators: Learning to Edit for Requirement Compliance](https://mlsanity.com/paper/2512.15469/) (2025)

## Abstract (arXiv)

In domains with high stakes such as law, recruitment, and healthcare, learning models frequently rely on sensitive user data for inference, necessitating the complete set of features. This not only poses significant privacy risks for individuals but also demands substantial human effort from organizations to verify information accuracy. This paper asks whether it is necessary to use all input features for accurate predictions at inference time. The paper demonstrates that, in a personalized setting, individuals may only need to disclose a small subset of their features without compromising decision-making accuracy. The paper also provides an efficient sequential algorithm to determine the appropriate attributes for each individual to provide. Evaluations across various learning tasks show that individuals can potentially report as little as 10% of their information while maintaining the same accuracy level as a model that employs the full set of user information.