Differentially Private Data Release on Graphs: Inefficiencies and Unfairness
Not on the map. Why?
Abstract (arXiv)
Networks are crucial components of many sectors, including telecommunications, healthcare, finance, energy, and transportation.The information carried in such networks often contains sensitive user data, like location data for commuters and packet data for online users. Therefore, when considering data release for networks, one must ensure that data release mechanisms do not leak information about individuals, quantified in a precise mathematical sense. Differential Privacy (DP) is the widely accepted, formal, state-of-the-art technique, which has found use in a variety of real-life settings including the 2020 U.S. Census, Apple users' device data, or Google's location data. Yet, the use of DP comes with new challenges, as the noise added for privacy introduces inaccuracies or biases and further, DP techniques can also distribute these biases disproportionately across different populations, inducing fairness issues. The goal of this paper is to characterize the impact of DP on bias and unfairness in the context of releasing information about networks, taking a departure from previous work which has studied these effects in the context of private population counts release (such as in the U.S. Census). To this end, we consider a network release problem where the network structure is known to all, but the weights on edges must be released privately. We consider the impact of this private release on a simple downstream decision-making task run by a third-party, which is to find the shortest path between any two pairs of nodes and recommend the best route to users. This setting is of highly practical relevance, mirroring scenarios in transportation networks, where preserving privacy while providing accurate routing information is crucial. Our work provides theoretical foundations and empirical evidence into the bias and unfairness arising due to privacy in these networked decision problems.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 31 references that are in the map. First posted on arXiv 8 Aug 2024.
Builds on
19 of 31 references.
References · 19
- 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
- 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
- 2020Characterising Bias in Compressed Modelscited by 162
- 2020To be Robust or to be Fair: Towards Fairness in Adversarial Trainingcited by 137
- 2018Differentially Private Fair Learningcited by 76
- 2019Fair Decision Making using Privacy-Protected Datacited by 58
- 2020Fairness Through Robustness: Investigating Robustness Disparity in Deep Learningcited by 55
- 2020Differentially Private and Fair Deep Learning: A Lagrangian Dual Approachcited by 53
- 2022Differential Privacy and Fairness in Decisions and Learning Tasks: A Surveycited by 47
- 2020Fair Learning with Private Demographic Datacited by 46
- 2022Pruning has a disparate impact on model accuracycited by 43
- 2021Decision Making with Differential Privacy under a Fairness Lenscited by 32
7 more
- 2020Bias and Variance of Post-processing in Differential Privacycited by 14
- 2022Post-processing of Differentially Private Data: A Fairness Perspectivecited by 9
- 2022SF-PATE: Scalable, Fair, and Private Aggregation of Teacher Ensemblescited by 8
- 2015Shortest Paths and Distances with Differential Privacycited by 6
- 2022Fairness Increases Adversarial Vulnerabilitycited by 5
- 2023On the Fairness Impacts of Private Ensembles Modelscited by 4
- 2022Differentially Private All-Pairs Shortest Path Distances: Improved Algorithms and Lower Boundscited by 2
Built on by
Not cited yet.