Nowadays, people heavily rely on the Internet for various activities, such as e-commerce (e.g., online shopping) and online banking. While online transactions are practical, they also provide scammers with a new way to exploit unsuspecting individuals. This study and investigation utilized data from ChaladOhn, a website designed and developed by academics and policemen. The data covered the period from February 2022 to January 2023. After analyzing and investigating, the results reveal that the total losses amounted to over 3,100 million Thai Baht, with each case incurring losses of less than 10 million. Furthermore, the investigation discovered the involvement of the top two banks in the market, KB*** and BB*, in the fraud. These banks accounted for: 1) 28.2% and 16.0% of the total number of scam accounts, 2) 25.6% and 20.5% of the total transactions, and 3) 35.7% and 14.9% of the total losses from the victims as recorded in the database, respectively. Considering the anticipated deterioration of this issue, it is crucial to inform regulators and relevant organizations about the investigation's findings. This will enable the development, suggestion, and implementation of an efficient solution to address the rapidly increasing number of online scam cases.
相關內容
《計算機信息》雜志發表高質量的論文，擴大了運籌學和計算的范圍，尋求有關理論、方法、實驗、系統和應用方面的原創研究論文、新穎的調查和教程論文，以及描述新的和有用的軟件工具的論文。官網鏈接： ·
MoDELS
·
Neural Networks
·
Performer
·
Subspace
·
The representations of neural networks are often compared to those of biological systems by performing regression between the neural network responses and those measured from biological systems. Many different state-of-the-art deep neural networks yield similar neural predictions, but it remains unclear how to differentiate among models that perform equally well at predicting neural responses. To gain insight into this, we use a recent theoretical framework that relates the generalization error from regression to the spectral bias of the model activations and the alignment of the neural responses onto the learnable subspace of the model. We extend this theory to the case of regression between model activations and neural responses, and define geometrical properties describing the error embedding geometry. We test a large number of deep neural networks that predict visual cortical activity and show that there are multiple types of geometries that result in low neural prediction error as measured via regression. The work demonstrates that carefully decomposing representational metrics can provide interpretability of how models are capturing neural activity and points the way towards improved models of neural activity.
The study of complex networks has significantly advanced our understanding of community structures which serves as a crucial feature of real-world graphs. Detecting communities in graphs is a challenging problem with applications in sociology, biology, and computer science. Despite the efforts of an interdisciplinary community of scientists, a satisfactory solution to this problem has not yet been achieved. This review article delves into the topic of community detection in graphs, which serves as a crucial role in understanding the organization and functioning of complex systems. We begin by introducing the concept of community structure, which refers to the arrangement of vertices into clusters, with strong internal connections and weaker connections between clusters. Then, we provide a thorough exposition of various community detection methods, including a new method designed by us. Additionally, we explore real-world applications of community detection in diverse networks. In conclusion, this comprehensive review provides a deep understanding of community detection in graphs. It serves as a valuable resource for researchers and practitioners in multiple disciplines, offering insights into the challenges, methodologies, and applications of community detection in complex networks.
Data analysis often involves the comparison of complex objects. With the ever increasing amounts and complexity of data, the demand for systems to help with these comparisons is also growing. Increasingly, information visualization tools support such comparisons explicitly, beyond simply allowing a viewer to examine each object individually. In this paper, we argue that the design of information visualizations of complex objects can, and should, be studied in general, that is independently of what those objects are. As a first step in developing this general understanding of comparison, we propose a general taxonomy of visual designs for comparison that groups designs into three basic categories, which can be combined. To clarify the taxonomy and validate its completeness, we provide a survey of work in information visualization related to comparison. Although we find a great diversity of systems and approaches, we see that all designs are assembled from the building blocks of juxtaposition, superposition and explicit encodings. This initial exploration shows the power of our model, and suggests future challenges in developing a general understanding of comparative visualization and facilitating the development of more comparative visualization tools.
Users rely on search engines for information in critical contexts, such as public health emergencies. Understanding how users evaluate the trustworthiness of search results is therefore essential. Research has identified rank and the presence of misinformation as factors impacting perceptions and click behavior in search. Here, we elaborate on these findings by measuring the effects of rank and misinformation, as well as warning banners, on the perceived trustworthiness of individual results in search. We conducted three online experiments (N=3196) using Covid-19-related queries to address this question. We show that although higher-ranked results are clicked more often, they are not more trusted. We also show that misinformation did not change trust in accurate results below it. However, a warning about unreliable sources backfired, decreasing trust in accurate information but not misinformation. This work addresses concerns about how people evaluate information in search, and illustrates the dangers of generic prevention approaches.
Breached data refers to the unauthorized access, theft, or exposure of confidential or sensitive information. Breaches typically occur when malicious actors or unauthorized users breach secure systems or networks, resulting in compromised personally identifiable information (PII), protected or personal health information (PHI), payment card industry (PCI) information, or other sensitive data. Data breaches are often the result of malicious activities such as hacking, phishing, insider threats, malware, or physical theft. The misuse of breached data can lead to identity theft, fraud, spamming, or blackmailing. Organizations that experience data breaches may face legal and financial consequences, reputational damage, and harm to their customers or users. Breached records are commonly sold on the dark web or made available on various public forums. To counteract these malicious activities, it is possible to collect breached databases and mitigate potential harm. These databases can be quite large, reaching sizes of up to 150 GB or more. Typically, breached data is stored in the CSV (Comma Separated Value) format due to its simplicity and lightweight nature, which reduces storage requirements. Analyzing and traversing large breached databases necessitates substantial computational power. However, this research explores techniques to optimize database traversal speed without the need to rent expensive cloud machines or virtual private servers (VPS). This optimization will enable individual security researchers to analyze and process large databases on their personal computer systems while significantly reducing costs.
Learning on big data brings success for artificial intelligence (AI), but the annotation and training costs are expensive. In future, learning on small data is one of the ultimate purposes of AI, which requires machines to recognize objectives and scenarios relying on small data as humans. A series of machine learning models is going on this way such as active learning, few-shot learning, deep clustering. However, there are few theoretical guarantees for their generalization performance. Moreover, most of their settings are passive, that is, the label distribution is explicitly controlled by one specified sampling scenario. This survey follows the agnostic active sampling under a PAC (Probably Approximately Correct) framework to analyze the generalization error and label complexity of learning on small data using a supervised and unsupervised fashion. With these theoretical analyses, we categorize the small data learning models from two geometric perspectives: the Euclidean and non-Euclidean (hyperbolic) mean representation, where their optimization solutions are also presented and discussed. Later, some potential learning scenarios that may benefit from small data learning are then summarized, and their potential learning scenarios are also analyzed. Finally, some challenging applications such as computer vision, natural language processing that may benefit from learning on small data are also surveyed.
We consider the problem of explaining the predictions of graph neural networks (GNNs), which otherwise are considered as black boxes. Existing methods invariably focus on explaining the importance of graph nodes or edges but ignore the substructures of graphs, which are more intuitive and human-intelligible. In this work, we propose a novel method, known as SubgraphX, to explain GNNs by identifying important subgraphs. Given a trained GNN model and an input graph, our SubgraphX explains its predictions by efficiently exploring different subgraphs with Monte Carlo tree search. To make the tree search more effective, we propose to use Shapley values as a measure of subgraph importance, which can also capture the interactions among different subgraphs. To expedite computations, we propose efficient approximation schemes to compute Shapley values for graph data. Our work represents the first attempt to explain GNNs via identifying subgraphs explicitly and directly. Experimental results show that our SubgraphX achieves significantly improved explanations, while keeping computations at a reasonable level.
Deep neural networks (DNNs) are successful in many computer vision tasks. However, the most accurate DNNs require millions of parameters and operations, making them energy, computation and memory intensive. This impedes the deployment of large DNNs in low-power devices with limited compute resources. Recent research improves DNN models by reducing the memory requirement, energy consumption, and number of operations without significantly decreasing the accuracy. This paper surveys the progress of low-power deep learning and computer vision, specifically in regards to inference, and discusses the methods for compacting and accelerating DNN models. The techniques can be divided into four major categories: (1) parameter quantization and pruning, (2) compressed convolutional filters and matrix factorization, (3) network architecture search, and (4) knowledge distillation. We analyze the accuracy, advantages, disadvantages, and potential solutions to the problems with the techniques in each category. We also discuss new evaluation metrics as a guideline for future research.
Deep convolutional neural networks (CNNs) have recently achieved great success in many visual recognition tasks. However, existing deep neural network models are computationally expensive and memory intensive, hindering their deployment in devices with low memory resources or in applications with strict latency requirements. Therefore, a natural thought is to perform model compression and acceleration in deep networks without significantly decreasing the model performance. During the past few years, tremendous progress has been made in this area. In this paper, we survey the recent advanced techniques for compacting and accelerating CNNs model developed. These techniques are roughly categorized into four schemes: parameter pruning and sharing, low-rank factorization, transferred/compact convolutional filters, and knowledge distillation. Methods of parameter pruning and sharing will be described at the beginning, after that the other techniques will be introduced. For each scheme, we provide insightful analysis regarding the performance, related applications, advantages, and drawbacks etc. Then we will go through a few very recent additional successful methods, for example, dynamic capacity networks and stochastic depths networks. After that, we survey the evaluation matrix, the main datasets used for evaluating the model performance and recent benchmarking efforts. Finally, we conclude this paper, discuss remaining challenges and possible directions on this topic.
The era of big data provides researchers with convenient access to copious data. However, people often have little knowledge about it. The increasing prevalence of big data is challenging the traditional methods of learning causality because they are developed for the cases with limited amount of data and solid prior causal knowledge. This survey aims to close the gap between big data and learning causality with a comprehensive and structured review of traditional and frontier methods and a discussion about some open problems of learning causality. We begin with preliminaries of learning causality. Then we categorize and revisit methods of learning causality for the typical problems and data types. After that, we discuss the connections between learning causality and machine learning. At the end, some open problems are presented to show the great potential of learning causality with data.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191