Interaction-Aware Parameter Privacy-Preserving Data Sharing in Coupled Systems via Particle Filter Reinforcement Learning

Haokun Yu, Jingyuan Zhou, Kaidi Yang
Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, PMLR 283:1525-1536, 2025.

Abstract

This paper addresses the problem of parameter privacy-preserving data sharing in coupled systems, where a data provider shares data with a data user but wants to protect its sensitive parameters. The shared data affects not only the data user’s decision-making but also the data provider’s operations through system interactions. To trade off control performance and privacy, we propose an interaction-aware privacy-preserving data sharing approach. Our approach generates distorted data by minimizing a combination of (i) mutual information that quantifies the privacy leakage of sensitive parameters and (ii) the impact of distorted data on the data provider’s control performance, considering the interactions between stakeholders. The optimization problem is formulated into a Bellman equation and solved by a particle filter reinforcement learning (RL)-based approach. Compared to existing RL-based methods, our formulation significantly reduces history dependency and efficiently handles scenarios with continuous state space. The proposed method is validated in a mixed-autonomy platoon scenario, where it successfully protects sensitive driving behavior parameters of human-driven vehicles (HDVs) against inference attacks while maintaining negligible impact on fuel efficiency.

Cite this Paper

BibTeX
@InProceedings{pmlr-v283-yu25a, title = {Interaction-Aware Parameter Privacy-Preserving Data Sharing in Coupled Systems via Particle Filter Reinforcement Learning}, author = {Yu, Haokun and Zhou, Jingyuan and Yang, Kaidi}, booktitle = {Proceedings of the 7th Annual Learning for Dynamics \& Control Conference}, pages = {1525--1536}, year = {2025}, editor = {Ozay, Necmiye and Balzano, Laura and Panagou, Dimitra and Abate, Alessandro}, volume = {283}, series = {Proceedings of Machine Learning Research}, month = {04--06 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v283/main/assets/yu25a/yu25a.pdf}, url = {https://proceedings.mlr.press/v283/yu25a.html}, abstract = {This paper addresses the problem of parameter privacy-preserving data sharing in coupled systems, where a data provider shares data with a data user but wants to protect its sensitive parameters. The shared data affects not only the data user’s decision-making but also the data provider’s operations through system interactions. To trade off control performance and privacy, we propose an interaction-aware privacy-preserving data sharing approach. Our approach generates distorted data by minimizing a combination of (i) mutual information that quantifies the privacy leakage of sensitive parameters and (ii) the impact of distorted data on the data provider’s control performance, considering the interactions between stakeholders. The optimization problem is formulated into a Bellman equation and solved by a particle filter reinforcement learning (RL)-based approach. Compared to existing RL-based methods, our formulation significantly reduces history dependency and efficiently handles scenarios with continuous state space. The proposed method is validated in a mixed-autonomy platoon scenario, where it successfully protects sensitive driving behavior parameters of human-driven vehicles (HDVs) against inference attacks while maintaining negligible impact on fuel efficiency.} }
Endnote
%0 Conference Paper %T Interaction-Aware Parameter Privacy-Preserving Data Sharing in Coupled Systems via Particle Filter Reinforcement Learning %A Haokun Yu %A Jingyuan Zhou %A Kaidi Yang %B Proceedings of the 7th Annual Learning for Dynamics \& Control Conference %C Proceedings of Machine Learning Research %D 2025 %E Necmiye Ozay %E Laura Balzano %E Dimitra Panagou %E Alessandro Abate %F pmlr-v283-yu25a %I PMLR %P 1525--1536 %U https://proceedings.mlr.press/v283/yu25a.html %V 283 %X This paper addresses the problem of parameter privacy-preserving data sharing in coupled systems, where a data provider shares data with a data user but wants to protect its sensitive parameters. The shared data affects not only the data user’s decision-making but also the data provider’s operations through system interactions. To trade off control performance and privacy, we propose an interaction-aware privacy-preserving data sharing approach. Our approach generates distorted data by minimizing a combination of (i) mutual information that quantifies the privacy leakage of sensitive parameters and (ii) the impact of distorted data on the data provider’s control performance, considering the interactions between stakeholders. The optimization problem is formulated into a Bellman equation and solved by a particle filter reinforcement learning (RL)-based approach. Compared to existing RL-based methods, our formulation significantly reduces history dependency and efficiently handles scenarios with continuous state space. The proposed method is validated in a mixed-autonomy platoon scenario, where it successfully protects sensitive driving behavior parameters of human-driven vehicles (HDVs) against inference attacks while maintaining negligible impact on fuel efficiency.
APA
Yu, H., Zhou, J. & Yang, K.. (2025). Interaction-Aware Parameter Privacy-Preserving Data Sharing in Coupled Systems via Particle Filter Reinforcement Learning. Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, in Proceedings of Machine Learning Research 283:1525-1536 Available from https://proceedings.mlr.press/v283/yu25a.html.

Related Material