The digitization of college student management is a crucial approach for training institutions to decrease management costs while enhancing the quality of students’ development. In this study, we focused on the students majoring in Computer Science in a certain university and conducted an exploration using their scores in multiple undergraduate courses. Initially, we selected the students’ basic and core academic courses based on the training program and identified four groups of course combinations with strong positive correlations through correlation and cluster analysis. This finding helped the university optimize the arrangement and structure of the Computer Science major’s course system. Next, we organized the student overall course performance data in a sequential format based on the semester order. Multiple machine learning models were utilized to perform regression prediction for student performance and classification prediction tasks to determine the student’s performance level. Finally, we integrated multiple machine learning models to create a practical framework for predicting student academic performance, which can be applied in student digital management. The framework can also provide effective decision support for academic early warning and guide the students’ development.
Ciphertext policy attribute-based encryption (CP-ABE) is a potential solution to security sharing issues since it offers one-to-many encryption and fine-grained access control. To prevent users from disclosing their access permissions, traceable CP-ABE schemes are emerging. However, the current traceable CP-ABE schemes still have some security problems, such as impromptu attribute retracting, unreliable tracking, and easy disclosure of access policy privacy, making it essential to implement dynamic data security sharing and malicious user auditing. To address these issues, we propose an auditable and dynamic access control scheme with behavior and identity tracing. The scheme first uses an access tree with hidden leaf nodes to express the access policy, improving the flexibility and security of access control. Secondly, the Blockchain and InterPlanetary File System (IPFS) frameworks perform the audit authentication and store the ciphertext, policy, and public keys to avoid tampering with shared data. Furthermore, to prevent users from leaking their decryption keys, a tracing algorithm based on white-box traceability is developed. On this basis, an authority update algorithm is proposed to revoke the malicious user’s permission immediately and update the decrypted key for unrevoked users. An auditable smart contract based on blockchain is proposed to prevent user denial. Finally, theoretical analyses prove that the proposed scheme not only achieves traceability, revocation , authority updating, policy hiding, and audit, but also guarantees security under a chosen plaintext attack model. Experiments demonstrate that our proposal reduces the key generation time by 22.6%, the encryption and decryption time by 39.2% and 59.8%, and the storage costs of ciphertext and private key are reduced by 12.1% and 5.6% over existing schemes.
Searchable encryption (SE) and attribute-based SE (ABSE) enable accurate encrypted data searches in cloud storage but face challenges, such as supporting only unidirectional verification. Additionally, ABSE lacks support for fuzzy search and unduly restricts search privileges, while SE schemes suffer from low-search efficiency and poor fuzzy search accuracy. To address these issues, the proposed scheme introduces a fuzzy retrieval mechanism with bidirectional verification and privacy protection. We constructed an on-chain and off-chain collaborative storage model to ensure the secure storage of massive data while enhancing access control flexibility by separating search authority from decryption authority. Additionally, we proposed a high-precision multikeyword fuzzy search scheme that integrates an improved secure k-nearest neighbor (SKNN) algorithm, the SimHash algorithm, and the random projection locality-sensitive hash (RPLSH) model. We also designed a bidirectional verification strategy resistant to collusion attacks to prevent data owner repudiation and internal collusion. Finally, we proposed a personalized extreme privacy protection strategy to ensure differential privacy security for search results. Security analysis shows that the proposed scheme satisfies adaptive chosen-keyword semantic security and resists collusion attacks, effectively protecting user privacy and data security. Experimental results demonstrate that the precision rate of the proposed scheme improves by 14.4% and 9.3% compared to the traditional LSH+BF fuzzy search architecture and the VRFMS scheme, respectively. Additionally, the search efficiency of the proposed scheme increases by approximately 36% and 54% compared to the MKFS and FWSR schemes, respectively.
In the age of big data, ensuring data privacy while enabling efficient encrypted data retrieval has become a critical challenge. Traditional searchable encryption schemes face difficulties in handling complex semantic queries. Additionally, they typically rely on honest but curious cloud servers, which introduces the risk of repudiation. Furthermore, the combined operations of search and verification increase system load, thereby reducing performance. Traditional verification mechanisms, which rely on complex hash constructions, suffer from low verification efficiency. To address these challenges, this paper proposes a blockchain-based contextual semantic-aware ciphertext retrieval scheme with efficient verification. Building on existing single and multi-keyword search methods, the scheme uses vector models to semantically train the dataset, enabling it to retain semantic information and achieve context-aware encrypted retrieval, significantly improving search accuracy. Additionally, a blockchain-based updatable master-slave chain storage model is designed, where the master chain stores encrypted keyword indexes and the slave chain stores verification information generated by zero-knowledge proofs, thus balancing system load while improving search and verification efficiency. Finally, an improved non-interactive zero-knowledge proof mechanism is introduced, reducing the computational complexity of verification and ensuring efficient validation of search results. Experimental results demonstrate that the proposed scheme offers stronger security, balanced overhead, and higher search verification efficiency.
30 December 2025 in Journal of King Saud University Computer and Information Sciences
Addressing the limitations of dynamic access control in cloud computing and large-scale distributed systems with respect to conceptual drift, extreme data imbalance, and reuse of established rules, we propose a hierarchical dynamic access control approach. First, we design a log-driven ABAC rule extraction method, which builds a user–operation–resource graph, applies attention-based embedding learning to detect anomalies, and converts them into explicit rules through prefix grouping and pruning. Second, we propose Hybrid-P, an online–offline fusion method that combines offline probability and online neighbor context to make real-time decisions without retraining. Third, we propose a context-aware multi-layer decision mechanism that adds a three-level threshold to the usual binary scheme, thereby balancing availability and safety. Experimental results on BGL, HDFS, Hadoop, Spirit, and Thunderbird show an average 21% gain in ROC-AUC over each data set’s best classical baseline, PR-AUC improves by more than 3 times in extreme imbalance scenarios, per-request latency less than 50 ms, and the weighted structural complexity of the generated rules remains within 23.56-103.41. Consequently, our method ensures maintainable, adaptive, and real-time access control.