Differentially Private Graph Data Release: Inefficiencies & Unfairness

Ferdinando Fioretto, Diptangshu Sen, Juba Ziani
Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, PMLR 258:2602-2610, 2025.

Abstract

Networks in sectors like telecommunications and transportation often contain sensitive user data, requiring privacy enhancing technologies during data release to ensure privacy. While Differential Privacy (DP) is recognized as the leading standard for privacy preservation, its use comes with new challenges, as the noise added for privacy introduces inaccuracies or biases. DP techniques have also been found to distribute these biases disproportionately across different populations, inducing fairness issues. This paper investigates the effects of DP on bias and fairness when releasing network edge weights. We specifically examine how these privacy measures affect decision-making tasks, such as computing shortest paths, which are crucial for routing in transportation and communications networks, and provide both theoretical insights and empirical evidence on the inherent trade-offs between privacy, accuracy, and fairness for network data release.

Cite this Paper

BibTeX
@InProceedings{pmlr-v258-fioretto25a, title = {Differentially Private Graph Data Release: Inefficiencies & Unfairness}, author = {Fioretto, Ferdinando and Sen, Diptangshu and Ziani, Juba}, booktitle = {Proceedings of The 28th International Conference on Artificial Intelligence and Statistics}, pages = {2602--2610}, year = {2025}, editor = {Li, Yingzhen and Mandt, Stephan and Agrawal, Shipra and Khan, Emtiyaz}, volume = {258}, series = {Proceedings of Machine Learning Research}, month = {03--05 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v258/main/assets/fioretto25a/fioretto25a.pdf}, url = {https://proceedings.mlr.press/v258/fioretto25a.html}, abstract = {Networks in sectors like telecommunications and transportation often contain sensitive user data, requiring privacy enhancing technologies during data release to ensure privacy. While Differential Privacy (DP) is recognized as the leading standard for privacy preservation, its use comes with new challenges, as the noise added for privacy introduces inaccuracies or biases. DP techniques have also been found to distribute these biases disproportionately across different populations, inducing fairness issues. This paper investigates the effects of DP on bias and fairness when releasing network edge weights. We specifically examine how these privacy measures affect decision-making tasks, such as computing shortest paths, which are crucial for routing in transportation and communications networks, and provide both theoretical insights and empirical evidence on the inherent trade-offs between privacy, accuracy, and fairness for network data release.} }
Endnote
%0 Conference Paper %T Differentially Private Graph Data Release: Inefficiencies & Unfairness %A Ferdinando Fioretto %A Diptangshu Sen %A Juba Ziani %B Proceedings of The 28th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2025 %E Yingzhen Li %E Stephan Mandt %E Shipra Agrawal %E Emtiyaz Khan %F pmlr-v258-fioretto25a %I PMLR %P 2602--2610 %U https://proceedings.mlr.press/v258/fioretto25a.html %V 258 %X Networks in sectors like telecommunications and transportation often contain sensitive user data, requiring privacy enhancing technologies during data release to ensure privacy. While Differential Privacy (DP) is recognized as the leading standard for privacy preservation, its use comes with new challenges, as the noise added for privacy introduces inaccuracies or biases. DP techniques have also been found to distribute these biases disproportionately across different populations, inducing fairness issues. This paper investigates the effects of DP on bias and fairness when releasing network edge weights. We specifically examine how these privacy measures affect decision-making tasks, such as computing shortest paths, which are crucial for routing in transportation and communications networks, and provide both theoretical insights and empirical evidence on the inherent trade-offs between privacy, accuracy, and fairness for network data release.
APA
Fioretto, F., Sen, D. & Ziani, J.. (2025). Differentially Private Graph Data Release: Inefficiencies & Unfairness. Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 258:2602-2610 Available from https://proceedings.mlr.press/v258/fioretto25a.html.

Related Material