Privacy-Preserving Location Data Sharing in Mobile Online Social Networks

This paper proposed a hybrid privacy-preserving framework for location data sharing in mobile online social networks that integrates three mutually reinforcing layers: Federated Learning for structural privacy, ($\epsilon, \delta$)-Differential Privacy for algorithmic privacy, and Deep Reinforcement Learning for temporal obfuscation. The framework is anchored by a lightweight three-factor authentication protocol using Chebyshev chaotic maps, SHA-1 hash chains, and Fuzzy Extractor biometric binding, which eliminates dependence on PKI while achieving mutual authentication in 117.12 ms. Formal security is verified via BAN logic derivation in 17 steps, the Real-or-Random model, and ProVerif automated simulation, confirming resistance to twelve attack classes. Empirical evaluation on the GeoLife and T-Drive datasets demonstrates a 60–80% reduction in HMM-based de-anonymization success, less than 5% aggregate utility error, and less than 3% FL model accuracy degradation—collectively establishing a new state-of-the-art for privacy-utility balance in mOSN location sharing.

de Montjoye, Y.-A., Hidalgo, C. A., Verleysen, M., and Blondel, V. D., "Unique in the Crowd: The Privacy Bounds of Human Mobility," Scientific Reports, vol. 3, p. 1376, 2013.Zang, H. and Bolot, J., "Anonymization of Location Data Does Not Work: A Large-Scale Measurement Study," Proc. ACM MobiCom, pp. 145–156, 2011.Primault, V., Boutet, A., Mokhtar, S. B., and Brunie, L., "The Long Road to Computational Location Privacy: A Survey," IEEE Communications Surveys & Tutorials, vol. 21, no. 3, pp. 2772–2793, 2019.Bhattacharya, P., Tanwar, S., Shah, R., and Kumar, N., "A Privacy-Preserving Efficient Location-Sharing Scheme for Mobile Online Social Network Applications," IEEE Access, vol. 8, pp. 221330–221351, 2020.Gedik, B. and Liu, L., "Protecting Location Privacy with Personalized k-Anonymity: Architecture and Algorithms," IEEE Trans. Mobile Comput., vol. 7, no. 1, pp. 1–18, 2008.Gruteser, M. and Grunwald, D., "Anonymous Usage of Location-Based Services Through Spatial and Temporal Cloaking," Proc. ACM MobiSys, pp. 31–42, 2003.Dwork, C., "Differential Privacy," in Proc. ICALP, Lecture Notes in Computer Science, vol. 4052, pp. 1–12, 2006.Andrés, M. E., Bordenabe, N. E., Chatzikokolakis, K., and Palamidessi, C., "Geo-Indistinguishability: Differential Privacy for Location-Based Systems," Proc. ACM CCS, pp. 901–914, 2013.McMahan, B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B. A., "Communication-Efficient Learning of Deep Networks from Decentralized Data," Proc. AISTATS, pp. 1273–1282, 2017.