# Active Privacy-utility Trade-off Against a Hypothesis Testing Adversary

arXiv: https://arxiv.org/abs/2102.08308 · HTML: https://mlsanity.com/paper/2102.08308/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 25 references that are in the map.
- First posted on arXiv 16 Feb 2021.

## Builds on (most cited first, 7 of 7)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Policy Design for Active Sequential Hypothesis Testing using Deep Learning](https://mlsanity.com/paper/1810.04859/) (2018)
- [Privacy-Aware Time-Series Data Sharing with Deep Reinforcement Learning](https://mlsanity.com/paper/2003.02685/) (2020)
- [On-Average KL-Privacy and its equivalence to Generalization for Max-Entropy Mechanisms](https://mlsanity.com/paper/1605.02277/) (2016)
- [Quantifying Differential Privacy under Temporal Correlations](https://mlsanity.com/paper/1610.07543/) (2016)
- [Privacy-Aware Location Sharing with Deep Reinforcement Learning](https://mlsanity.com/paper/1907.07606/) (2019)
- [Privacy Against Brute-Force Inference Attacks](https://mlsanity.com/paper/1902.00329/) (2019)

## Built on by (most cited first, 6 of 6)

- [Privacy-Aware Communication Over a Wiretap Channel with Generative Networks](https://mlsanity.com/paper/2110.04094/) (2021)
- [Uncertainty-Autoencoder-Based Privacy and Utility Preserving Data Type Conscious Transformation](https://mlsanity.com/paper/2205.01950/) (2022)
- [Temporal Detection of Anomalies via Actor-Critic Based Controlled Sensing](https://mlsanity.com/paper/2201.00879/) (2022)
- [Initial Exploration of Zero-Shot Privacy Utility Tradeoffs in Tabular Data Using GPT-4](https://mlsanity.com/paper/2404.05047/) (2024)
- [Active Privacy-Utility Trade-off Against Inference in Time-Series Data Sharing](https://mlsanity.com/paper/2202.05833/) (2022)
- [Optimizing Privacy and Utility Tradeoffs for Group Interests Through Harmonization](https://mlsanity.com/paper/2404.05043/) (2024)

## Abstract (arXiv)

We consider a user releasing her data containing some personal information in return of a service. We model user's personal information as two correlated random variables, one of them, called the secret variable, is to be kept private, while the other, called the useful variable, is to be disclosed for utility. We consider active sequential data release, where at each time step the user chooses from among a finite set of release mechanisms, each revealing some information about the user's personal information, i.e., the true hypotheses, albeit with different statistics. The user manages data release in an online fashion such that maximum amount of information is revealed about the latent useful variable, while the confidence for the sensitive variable is kept below a predefined level. For the utility, we consider both the probability of correct detection of the useful variable and the mutual information (MI) between the useful variable and released data. We formulate both problems as a Markov decision process (MDP), and numerically solve them by advantage actor-critic (A2C) deep reinforcement learning (RL).