With the rapid growth of cloud computing, securely outsourcing sensitive data has become crucial for protecting user privacy. SQL, renowned for its expressiveness and flexibility, remains the predominant query language for big data analytics. However, existing access control mechanisms for encrypted SQL databases primarily operate at coarse granularity levels, such as databases, tables, or columns, failing to meet nuanced user access requirements at the individual data-element level. To address this challenge, we proposeEGuardSQL, a novel architecture that enables fine-grained, element-level access control over encrypted SQL tables. Our approach leverages Ciphertext-Policy Attribute-Based Encryption (CP-ABE) to define hybrid access policies that integrate both row-level and column-level permissions, facilitating precise and flexible control. To mitigate the inherent computational overhead associated with CP-ABE, particularly when dealing with complex policy structures, we introduce an optimized reusable sub-policy mechanism that effectively reduces redundant cryptographic computations during encryption and decryption processes. We formally prove the selective IND-CPA security of the EGuardSQL scheme under the decisional$q$-parallel Bilinear Diffie-Hellman Exponent (BDHE) assumption and demonstrate its resistance to collusion attacks. Comprehensive performance evaluations illustrate that EGuardSQL achieves significant improvements in computational and communication efficiency compared to conventional CP-ABE approaches, while maintaining low storage overhead and robust security guarantees.

Intelligent transportation systems (ITS) involve data management and operation among multiple parties, making the trustworthiness and transparency of centralized data a highly challenging issue. Blockchain data storage, characterized by its immutability and multi-party collaboration, has emerged as a mainstream technology for trustworthy data sharing among multiple parties. However, the current on-chain data structures based on transactions, e.g., Ethereum’s MPT, struggle to address the scalability and efficient on-chain and off-chain collaboration required for data management with high spatio-temporal characteristics, as seen in intelligent transportation. In this paper, we propose a spatio-temporal scalable Merkle Patricia Tree (sMPT) structure for hierarchical organization of on-chain data objects (DOs), which is mapped to the off-chain transportation data entries through a DO packaging mechanism. The experimental evaluation results demonstrate the effectiveness of the proposed sMPT structure in basic functionality, like on-chain storage and sMPT compression. In terms of efficiency, sMPT outperforms the original MPT in retrieval and verification, particularly in batch verification.