From See to Shield: ML-Assisted Fine-Grained Access Control for Visual Data

2025-10-22

AI Summary

To address the challenges of identifying sensitive regions and enforcing coarse-grained access control in large-scale visual data sharing, this paper proposes a policy-driven trusted data sharing architecture. The architecture integrates four core components: (1) automated sensitive region detection using machine learning, (2) post-hoc refinement for improved localization accuracy, (3) hybrid encryption—leveraging symmetric encryption for efficiency and attribute-based encryption (ABE) for fine-grained, policy-aware authorization—and (4) distributed key management. It enables dynamic identification and selective encryption of privacy-sensitive objects within images. Experiments on standard vision benchmarks demonstrate a 5% improvement in macro-averaged F1-score and a 10% gain in mean Average Precision (mAP). Policy-based decryption per image completes in under one second, achieving high accuracy, low latency, and strong scalability—validating its practical deployability.

Technology Category

• Computer Vision: Large Vision Models
• Machine Learning: Privacy
• Search and Optimization: Learning to Search

Application Category

• Security and Privacy: Data transparency and provenance
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

As the volume of stored data continues to grow, identifying and protecting sensitive information within large repositories becomes increasingly challenging, especially when shared with multiple users with different roles and permissions. This work presents a system architecture for trusted data sharing with policy-driven access control, enabling selective protection of sensitive regions while maintaining scalability. The proposed architecture integrates four core modules that combine automated detection of sensitive regions, post-correction, key management, and access control. Sensitive regions are secured using a hybrid scheme that employs symmetric encryption for efficiency and Attribute-Based Encryption for policy enforcement. The system supports efficient key distribution and isolates key storage to strengthen overall security. To demonstrate its applicability, we evaluate the system on visual datasets, where Privacy-Sensitive Objects in images are automatically detected, reassessed, and selectively encrypted prior to sharing in a data repository. Experimental results show that our system provides effective PSO detection, increases macro-averaged F1 score (5%) and mean Average Precision (10%), and maintains an average policy-enforced decryption time of less than 1 second per image. These results demonstrate the effectiveness, efficiency and scalability of our proposed solution for fine-grained access control.

Problem

• Automated detection and encryption of sensitive visual content
• Policy-driven access control for multi-user data sharing
• Scalable protection of privacy-sensitive objects in images

Innovation

• Hybrid encryption combines symmetric and attribute-based methods
• Automated detection and correction of sensitive image regions
• Modular architecture integrates key management with access control