注释,注释: The subject of the study is to identify effective methods of legislative work to counteract the use by telephone fraudsters of such technical means as illegal substitution of SIM cards and Internet services for substitution of incoming call numbers. The general scientific methodology of dialectical (meaningful) logic and comparative analysis of practical problems and legislative activity of federal authorities are used. Fraud causes huge damage to society and incurs huge costs to the state. The global spread of the Internet has allowed scammers to export their activities to a fast-growing market and attract previously untapped consumers. The evolution of technologies and the spread of fraudulent approaches on the Internet have exacerbated the problems faced by victims. The results serve as evidence that when detecting and timely stopping attempts at telephone fraud (suspending suspicious transactions), legislative support and the formation of a subordinate regulatory framework are necessary for the interaction of financial organizations, telecommunications operators and law enforcement agencies. The development of smartphones and cellular networks increases the need for mobile advertising and targeted marketing. However, it also causes invisible security threats. We have found that phone fraud with fake phone numbers with a very short service life is becoming more and more popular and is being used to deceive users. The article is devoted to the consideration of the problem of legal regulation to ensure information security. As phone fraud becomes more common, it is extremely important to understand how to increase the effectiveness of prevention. Conclusions are drawn about the need to strengthen the centralization of countering intruders in order to increase the effectiveness of preventing telephone fraud, following the example of creating an interbank digital platform "Know your Customer".

注释,注释: The subject of the study is the problem of legal prevention of the use of computer and telecommunication technologies by intruders in new financial remote services in Russia. An increase in the variety and volume of attacks is inevitable, given the desire of scammers to obtain personal and confidential information. In recent years, Russia has made significant progress in improving its infrastructure responsible for information security. The article is a comprehensive analysis of Russian legislation. The analytical review of various directions of development of the Russian federal legislation in recent years aimed at preventive counteraction, elimination of a number of conditions and prerequisites of cybercrime in the financial sphere is presented. Particular attention is paid to the jurisdictional aspects of Russian legislation. The government needs to make thorough preparations to counter a range of unwanted cyber events, both accidental and intentional. There are significant risks of local attacks and losses as a result of compromising computer and telecommunications services. The conclusions contain final proposals for further improvement of legislation taking into account foreign and international experience. The main conclusions of the study are the productivity of identifying the strategic prevention direction in preventive activities – preventive identification and elimination of gaps in the regulatory framework, as well as technical and organizational vulnerabilities that make possible various types of attacks and "schemes" of cybercriminals in the financial sphere.

注释,注释: В настоящее время генерируется огромное количество текстов, и существует острая необходимость организовать их в определенной структуре, для выполнения классификации и правильного определения категорий. Авторы подробно рассматривают такие аспекты темы как классификация текстов на естественном языке и определение тональности текста в социальной сети Twitter. Использование социальных сетей помимо многочисленных плюсов, несет и негативный характер, а именно пользователи сталкиваются с многочисленными киберугрозами, такими как утечка персональных данных, кибербуллинг, спам, фейковые новости. Основной задачей анализа тональности текста является определение эмоциональной наполненности и окраски, что позволит выявить негативно окрашенную тональность речи. Эмоциональная окраска или настроение являются сугубо индивидуальными чертами и, таким образом, несут потенциал в качестве инструментов идентификации.   Основная цель классификации текста на естественном языке состоит в том, чтобы извлекать информацию из текста и использовать такие процессы, как поиск, классификация с применением методов машинного обучения. Авторы отдельно выбрали и сравнили следующие модели: логистическая регрессия, многослойный перцептрон, случайный лес, наивный байесовский метод, метод K-ближайших соседей, дерево решений и стохастический градиентный спуск. Затем мы протестировали и проанализировали эти методы друг с другом. Экспериментальный вывод показывает, что применение скоринга TF-IDF для векторизации текста улучшает качество модели не всегда, либо делает это для отдельных метрик, вследствие чего уменьшается показатель остальных метрик для той или иной модели. Наилучшим методом для выполнения цели работы является Стохастический градиентный спуск.

Abstract: Currently, a huge number of texts are being generated, and there is an urgent need to organize them in a certain structure in order to perform classification and correctly define categories. The authors consider in detail such aspects of the topic as the classification of texts in natural language and the definition of the tonality of the text in the social network Twitter. The use of social networks, in addition to numerous advantages, also carries a negative character, namely, users face numerous cyber threats, such as personal data leakage, cyberbullying, spam, fake news. The main task of the analysis of the tonality of the text is to determine the emotional fullness and coloring, which will reveal the negatively colored tonality of speech. Emotional coloring or mood are purely individual traits and thus carry potential as identification tools. The main purpose of natural language text classification is to extract information from the text and use processes such as search, classification using machine learning methods. The authors separately selected and compared the following models: logistic regression, multilayer perceptron, random forest, naive Bayesian method, K-nearest neighbor method, decision tree and stochastic gradient descent. Then we tested and analyzed these methods with each other. The experimental conclusion shows that the use of TF-IDF scoring for text vectorization does not always improve the quality of the model, or it does it for individual metrics, as a result of which the indicator of the remaining metrics for a particular model decreases. The best method to accomplish the purpose of the work is Stochastic gradient descent.

注释,注释: The authors consider in detail the identification of cyberbullying, which is carried out by fraudsters with the illegal use of the victim's personal data. Basically, the source of this information is social networks, e-mails. The use of social networks in society is growing exponentially on a daily basis. The use of social networks, in addition to numerous advantages, also has a negative character, namely, users face numerous cyber threats. Such threats include the use of personal data for criminal purposes, cyberbullying, cybercrime, phishing and cyberbullying. In this article, we will focus on the task of identifying trolls. Identifying trolls on social networks is a difficult task because they are dynamic in nature and are collected in several billion records. One of the possible solutions to identify trolls is the use of machine learning algorithms. The main contribution of the authors to the study of the topic is the use of the method of identifying trolls in social networks, which is based on the analysis of the emotional state of network users and behavioral activity. In this article, in order to identify trolls, users are grouped together, this association is carried out by identifying a similar way of communication. The distribution of users is carried out automatically through the use of a special type of neural networks, namely self-organizing Kohonen maps. The group number is also determined automatically. To determine the characteristics of users, on the basis of which the distribution into groups takes place, the number of comments, the average length of the comment and the indicator responsible for the emotional state of the user are used.

注释,注释: Интернет возник как мощная инфраструктура для всемирной коммуникации и взаимодействия людей. Некоторое неэтичное использование этой технологии спам, фишинг, тролли, киберзапугивание, вирусы вызвало проблемы при разработке механизмов, гарантирующих доступные и безопасные возможности ее использования. В настоящее время проводится множество исследований обнаружения спама, фишинга. Выявление телефонного мошенничества стало критически важным, поскольку влечет огромные потери. Алгоритмы машинного обучения и обработки естественного языка используются для анализа огромного количества текстовых данных.
Выявление мошенников производится с применением интеллектуального анализа текста и может быть реализовано путем анализа терминов слова или фразы.    Одной из сложных задач является разделение этих огромных неструктурированных данных на кластеры. Для этих целей существует несколько моделей тематического моделирования. В данной статье представлено применение этих моделей, в частности LDA, LSI и NMF. Сформирован набор данных. Проведен предварительный анализ данных и построены признаки для моделей в задаче по распознаванию темы текста. Рассмотрены подходы извлечения ключевых фраз в задачах распознавания темы текста. Приведены ключевые понятия этих подходов. Показаны недостатки этих моделей, предложены направления по улучшению алгоритмов обработки текстов. Проведена оценки качества моделей. Усовершенствованы модели благодаря подбору гиперпараметра и изменению функции предобработки данных.

Abstract: The Internet has emerged as a powerful infrastructure for worldwide communication and human interaction. Some unethical use of this technology spam, phishing, trolls, cyberbullying, viruses caused problems in the development of mechanisms that guarantee affordable and safe opportunities for its use. Currently, many studies are being conducted to detect spam and phishing. The detection of telephone fraud has become critically important, as it entails huge losses. Machine learning and natural language processing algorithms are used to analyze a huge amount of text data.
Fraudsters are identified using text mining and can be implemented by analyzing the terms of a word or phrase. One of the difficult tasks is to divide this huge unstructured data into clusters. There are several thematic modeling models for these purposes. This article presents the application of these models, in particular LDA, LSI and NMF. A data set has been formed. A preliminary analysis of the data was carried out and signs were constructed for models in the task of recognizing the subject of the text. The approaches of keyword extraction in the tasks of text topic recognition are considered. The key concepts of these approaches are given. The disadvantages of these models are shown, and directions for improving text processing algorithms are proposed. The evaluation of the quality of the models was carried out. Improved models thanks to the selection of hyperparameters and changing the data preprocessing function.