Personalized Image Privacy Advisors via Federated Daisy-Chaining

Image sharing on social media has become routine but poses serious privacy risks, as users may unknowingly expose sensitive information. This necessitates an image privacy advisor that assigns personalized privacy risk scores, helping users decide whether to share images publicly or not. However, centralized training of such models risks user data exposure and loss of ownership, as data must be uploaded to a central server. To safeguard user privacy, we adopt Federated Learning (FL), which enables collaborative model training without sharing raw data. Despite its advantages, FL faces challenges such as data heterogeneity from diverse user privacy preferences, limited annotations per user, and communication overhead. To address these issues, we propose CFedDC, a personalized FL algorithm combined with PIONet, a parameter-efficient model with 14.18 $\times$ fewer trainable parameters and 92.94\% lower memory footprint than centralized baselines. CFedDC mitigates data heterogeneity through clustering and cluster aware regularization with stability, and tackles data scarcity using a daisy-chaining knowledge transfer mechanism. Comprehensive experimental evaluations demonstrate that our proposed method achieves well-aligned personalized user privacy scores, outperforming existing centralized and FL-based image privacy models.