Although most conventional methods of preserving data privacy focus on static datasets, which remain unchanged after processing, real-world datasets may be dynamically modified often. Therefore, privacy-preservation methods must maintain data privacy after dataset modification. Re-anonymization of entire datasets is inefficient when large datasets are frequently modified. Although several previous studies have addressed data privacy for incremental data updates (i.e., record insertions), they have not adequately it for dynamic changes made to existing datasets (i.e., record updates and deletions). Therefore, we identified limitations of data-privacy preservation for dynamically evolving datasets and used anatomy instead of generalization and suppression to develop a more efficient l-diversity algorithm for preserving privacy of such datasets. We also used a Cuckoo filter, a new probabilistic data structure for approximate set-membership tests, to improve data-processing efficiency. Experimental results demonstrated that our proposed data-anonymization algorithm processed data more efficiently than other conventional algorithms, requiring much less running time than conventional re-anonymization of entire datasets. The Cuckoo-filtered algorithm was especially efficient, dramatically reducing operation execution times while maintaining privacy of dynamically evolving datasets.

In recent years, complex machine learning and deep learning algorithms have been used in prognostics and health management applications to monitor the state of industrial systems in real-time and predict failures in advance. However, the performance of these algorithms depends on the size of the collected labeled datasets. This study proposes a semi-weakly supervised learning method that creates label functions using a small amount of data and, consequently, combines weak supervision and semi-supervision methods to expand the labeled dataset for training. The proposed model training method creates labels automatically in the life prediction dataset of rolling element bearings, which were manually labeled by expert groups. The performance of the deep neural network is continuously improved through experiments, and a performance improvement similar to that of manually labeled training data is presented. Future research applications include meta-learner experiments (e.g., use of pre-trained word embedding or other model architectures) and more appropriate selection methods and definitions for the basic learner.

Smart contracts are self-executing programs on blockchains that manage complex business logic with transparency and integrity. However, their immutability after deployment makes programming errors particularly critical, as such errors can be exploited to compromise blockchain security. Existing vulnerability detection methods often rely on fixed rules or target specific vulnerabilities, limiting their scalability and adaptability to diverse smart contract scenarios. Furthermore, natural language processing approaches for source code analysis frequently fail to capture program flow, which is essential for identifying structural vulnerabilities. To address these limitations, we propose a novel model that integrates textual and structural information for smart contract vulnerability detection. Our approach employs the CodeBERT NLP model for textual analysis, augmented with structural insights derived from control flow graphs created using the abstract syntax tree and opcode of smart contracts. Each graph node is embedded using Sent2Vec, and centrality analysis is applied to highlight critical paths and nodes within the code. The extracted features are normalized and combined into a prompt for a large language model to detect vulnerabilities effectivel. Experimental results demonstrate the superiority of our model, achieving an accuracy of 86.70%, a recall of 84.87%, a precision of 85.24%, and an F1-score of 84.46%. These outcomes surpass existing methods, including CodeBERT alone (accuracy: 81.26%, F1-score: 79.84%) and CodeBERT combined with abstract syntax tree analysis (accuracy: 83.48%, F1-score: 79.65%). The findings underscore the effectiveness of incorporating graph structural information alongside text-based analysis, offering improved scalability and performance in detecting diverse vulnerabilities.

Over the last several years, in parallel with the general global advancement in mobile technology and a rise in social media network content consumption, multimedia content production and reproduction has increased exponentially. Therefore, enabled by the rapid recent advancements in deep learning technology, research on scene graph generation is being actively conducted to more efficiently search for and classify images desired by users within a large amount of content. This approach lets users accurately find images they are searching for by expressing meaningful information on image content as nodes and edges of a graph. In this study, we propose a scene graph generation method based on using the Resource Description Framework (RDF) model to clarify semantic relations. Furthermore, we also use convolutional neural network (CNN) and recurrent neural network (RNN) deep learning models to generate a scene graph expressed in a controlled vocabulary of the RDF model to understand the relations between image object tags. Finally, we experimentally demonstrate through testing that our proposed technique can express semantic content more effectively than existing approaches.

Recent studies on change detection for RDF data have focused on minimizing the delta size and, as a way to exploit the semantics of RDF models in reducing the delta size, the forward-chaining inferences have been widely employed. However, since the forward-chaining inferences should pre-compute the entire closure of the RDF model, the existing approaches are not scalable to large RDF data sets. In this paper, we propose a scalable change detection scheme for RDF data, which is based on backward-chaining inference and pruning. Our scheme, instead of pre-computing the full closure, computes only the necessary closure on the fly, thus achieving fast and scalable change detection. In addition, for any two RDF data input files to be compared, the delta obtained from our scheme is always equivalent to the one from the existing forward-chaining inferences. In addition, in order to handle RDF data sets too large to fit in the available RAM, we present an SQL-based implementation of our scheme. Our experimental results show that our scheme, in comparison to the existing schemes, can reduce the number of inference triples for RDF change detection by 10–60%.