Fraudulent activities on blockchain networks threaten the integrity and reliability of decentralized finance ecosystems. Accurately identifying malicious nodes such as phishing or ransomware addresses, within large-scale blockchain transaction graphs remains a critical challenge due to their dynamic, sparse, and continuously evolving topologies. Transfer learning offers a powerful paradigm for fraud detection because many fraudulent schemes, including ransomware and phishing, are often orchestrated by overlapping actor groups that share behavioral and structural patterns across networks. Leveraging these shared representations enables knowledge transfer from previously observed fraud types to emerging ones. However, the complex and multi-modal nature of digital financial systems introduces substantial challenges for graph-based transfer learning. Fraudulent activities are shaped by diverse modalities including graph structure, transaction sequences, temporal price dynamics, and textual metadata, while distributional shifts frequently occur across time and platforms. Existing graph transfer learning methods struggle to model such multi-modal dependencies and to align divergent feature distributions. To tackle these challenges, we develop a Multi-mOdal Enhanced Graph Transfer Learning (MOE-GTL) framework which incorporates graph, temporal, and textual modalities for fraudulent node detection. We further introduce Temporal-aware Maximum Mean Discrepancy (TMMD), a regularization mechanism that explicitly aligns multi-modal feature distributions between source and target graphs over time. Extensive experiments reveal that our MOE-GTL model notably improves the accuracy of fraudulent node classifications on Ethereum and Solana transaction graphs.

Fraudulent activity on blockchain networks poses significant risks to the integrity and trust of decentralized finance ecosystems. The timely and accurate detection of fraud nodes such as phishing addresses within large-scale Ethereum transaction networks remains a major challenge due to their dynamic, sparse, and evolving structures. While methods like graph deep learning (e.g., graph neural networks) have been extensively explored, they are not inherently designed to capture higherorder interactions and textual information embedded within graph data. Motivated by the urgent need for advanced and robust fraud detection techniques, we introduce a novel graph prompting method named Large Language Model-Simplicial Complex (LLM-SC) based graph prompting framework that leverages LLM-based multi-agent collaboration system, LLMbased financial news prompt function, and simplicial neural networks to capture both the structural and contextual dimensions of blockchain activity. The empirical studies demonstrate the effectiveness of our approach, and these results provide a new tool for blockchain analytics platforms and regulatory authorities, enabling earlier and more accurate identification of fraudulent behavior and ultimately supporting safer and more resilient digital financial systems. The code is available at https://github.com/y13564/LLM-SC.

Industrial Information Technology infrastructures are often vulnerable to cyberattacks. To ensure security to the computer systems in an industrial environment, it is required to build effective intrusion detection systems to monitor the cyber-physical systems (e.g., computer networks) in the industry for malicious activities. This article aims to build such intrusion detection systems to protect the computer networks from cyberattacks. More specifically, we propose a novel unsupervised machine learning approach that combines the K-Means algorithm with the Isolation Forest for anomaly detection in industrial big data scenarios. Since our objective is to build the intrusion detection system for the big data scenario in the industrial domain, we utilize the Apache Spark framework to implement our proposed model that was trained in large network traffic data (about 123 million instances of network traffic) stored in Elasticsearch. Moreover, we evaluate our proposed model on the live streaming data and find that our proposed system can be used for real-time anomaly detection in the industrial setup. In addition, we address different challenges that we face while training our model on large datasets and explicitly describe how these issues were resolved. Based on our empirical evaluation in different use cases for anomaly detection in real-world network traffic data, we observe that our proposed system is effective to detect anomalies in big data scenarios. Finally, we evaluate our proposed model on several academic datasets to compare with other models and find that it provides comparable performance with other state-of-the-art approaches.

The severe pneumonia induced by the infection of the SARS-CoV-2 virus causes massive death in the ongoing COVID-19 pandemic. The early detection of the SARS-CoV-2 induced pneumonia relies on the unique patterns of the chest XRay images. Deep learning is a data-greedy algorithm to achieve high performance when adequately trained. A common challenge for machine learning in the medical domain is the accessibility to properly annotated data. In this study, we apply a conditional adversarial network (cGAN) to perform image to image (Pix2Pix) translation from the non-COVID-19 chest X-Ray domain to the COVID-19 chest X-Ray domain. The objective is to learn a mapping from the normal chest X-Ray visual patterns to the COVID-19 pneumonia chest X-ray patterns. The original dataset has a typical imbalanced issue because it contains only 219 COVID-19 positive images but has 1,341 images for normal chest X-Ray and 1,345 images for viral pneumonia. A U-Net based architecture is applied for the image-to-image translation to generate synthesized COVID-19 X-Ray chest images from the normal chest X-ray images. A 50-convolutional-layer residual net (ResNet) architecture is applied for the final classification task. After training the GAN model for 100 epochs, we use the GAN generator to translate 1,100 COVID-19 images from the normal X-Ray to form a balanced training dataset (3,762 images) for the classification task. The ResNet based classifier trained by the enhanced dataset achieves the classification accuracy of 97.8% compared to 96.1% in the transfer learning mode. When trained with the original imbalanced dataset, the model achieves an accuracy of 96.1% compared to 95.6% in the training from trainby-scratch model. In addition, the classifier trained by the enhanced dataset has more stable measures in precision, recall, and F1 scores across different image classes. We conclude that the GAN-based data enhancement strategy is applicable to most medical image pattern recognition tasks, and it provides an effective way to solve the common expertise dependence issue in the medical domain.

Patient entity recognition or patient entity extraction is to detect the relevant electronic health records (EHRs) across multiple data sources belonging to an identical patient, and to link the relevant data together. Patient entity recognition is a useful technology for cross-system electronic health data analysis to define commonality, to synthesize multiple data sources, and to reduce data redundancy. In this paper, we propose a deep learning solution, a sequential LSTM + Word Embedding network model (WE + LSTM) to filter and represent the non-structured electronic health records by measuring their context similarity and link them to the identical patient entities. The text context features are at first filtered by a trained bidirectional LSTM network to filter the irrelevant patient entities, and the related patient information context is estimated by a trained shallow word embedding network for its word vector similarity with the existing entities in the database. Finally, the new input patient data will be linked to the existing patient entity in the dataset with the greatest context similarity. Our hypothesis is that the records pointing to the identical patient have closest context similarity, so the patterns can be encoded by a trained word embedding network. An infection disease registration dataset (5304 patient entities) is used to evaluate the performance of the proposed WE+LSTM model. The classification accuracy is 0.837 and the F score is 0.843, which is the highest compared to the comparators including a single word embedding model, a random forest model, and a conventional neural network model. In addition, the WE + LSTM model has the greatest AUG area when the ROC of the four models are compared. This result indicates the proposed WE + LSTM model provides a feasible solution to correctly recognize the patient identities from electronic records by measure the text context similarity. It provides a solution for patient identity recognition through multi-source health big data integration, which is an urgent task for health big data projects.

Data quality control is one of the most time consuming activities within Research Infrastructures (RIs), especially when involving observational data and multiple data providers. In this work we report on our ongoing development of data rogues, a scalable approach to manage data quality issues for observational data within RIs. The motivation for this work started with the creation of the FLUXNET2015 dataset, which includes carbon, water, and energy fluxes plus micrometeorological and ancillary data measured in over 200 sites around the world. To create an uniform dataset, including derived data products, extensive work on data quality control was needed. The unpredictable nature of observational data quality issues makes the automation of data quality control inherently difficult. Developed based on this experience, the data rogues methodology allows for increased automation of quality control activities by systematically identifying, cataloging, and documenting implementations of solutions to data issues. We believe this methodology can be extended and applied to others domains and types of data, making the automation of data quality control a more tractable problem.

Over the last several years, studies of instant messaging have observed its increasing role in the workplace[1] and in social situations[2]. We propose that modifying applications to interact with users over Instant Messaging (as IM bots) extends the collaborative benefits of IM into new areas. As IM Bots participating in group chatrooms, applications that had previously been restricted to a single user command line are able to engage in many to many interactions between users and applications. Current command line oriented user interfaces can be made into collaborative interfaces that exhibit (at a basic level) the ethnomethodological property of accountability as well as supporting legitimate peripheral participation.

VERN is an online collaborative tool that coordinates and distributes the process of finding optimal meeting times across the members of a group. The system combines the underlying democratic process inherent in email chain conversations with a remapping of the voting process to a calendar-based graphical user interface. As an alternative to existing forms of constrained democracy in which members vote from a previously defined set of options, we offer VERN as a case study for the potential of using a visual interface to enable all group members to contribute equally without constraints to the group decision making process.