• Smart Media Journal
• /
• v.11 no.1
• /
• pp.58-66
• /
• 2022

As Internet technology develops, SNS users are increasing. As SNS becomes popular, SNS-type crimes using the influence and anonymity of social networks are increasing day by day. In this paper, we propose a fake account classification method that applies machine learning and deep learning to statistical and image data for fake accounts classification. SNS account data used for training was collected by itself, and the collected data is based on statistical data and image data. In the case of statistical data, machine learning and multi-layer perceptron were employed to train. Furthermore in the case of image data, a convolutional neural network (CNN) was utilized. Accordingly, it was confirmed that the overall performance of account classification was significantly meaningful.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.4
• /
• pp.179-188
• /
• 2023

Recently, fake news disguises the form of news content and appears whenever important events occur, causing social confusion. Accordingly, artificial intelligence technology is used as a research to detect fake news. Fake news detection approaches such as automatically recognizing and blocking fake news through natural language processing or detecting social media influencer accounts that spread false information by combining with network causal inference could be implemented through deep learning. However, fake news detection is classified as a difficult problem to solve among many natural language processing fields. Due to the variety of forms and expressions of fake news, the difficulty of feature extraction is high, and there are various limitations, such as that one feature may have different meanings depending on the category to which the news belongs. In this paper, emotional change patterns are presented as an additional identification criterion for detecting fake news. We propose a model with improved performance by applying a convolutional neural network to a fake news data set to perform analysis based on content characteristics and additionally analyze emotional change patterns. Sentimental polarity is calculated for the sentences constituting the news and the result value dependent on the sentence order can be obtained by applying long-term and short-term memory. This is defined as a pattern of emotional change and combined with the content characteristics of news to be used as an independent variable in the proposed model for fake news detection. We train the proposed model and comparison model by deep learning and conduct an experiment using a fake news data set to confirm that emotion change patterns can improve fake news detection performance.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.5
• /
• pp.1179-1195
• /
• 2018

Recently, a variety of attacks on web services have been occurring through a multiple access environment such as PC, tablet, and smartphone. These attacks are causing various subsequent damages such as online fraud transactions, takeovers and theft of accounts, fraudulent logins, and information leakage through web service vulnerabilities. Creating a new fake account for Fraud attacks, hijacking accounts, and bypassing IP while using other usernames or email addresses is a relatively easy attack method, but it is not easy to detect and block these attacks. In this paper, we have studied a method to detect online fraud transaction and obsession by identifying and managing devices accessing web service using web-based device fingerprinting. In particular, it has been proposed to identify devices and to manage them by scoring process. In order to secure the validity of the proposed scheme, we analyzed the application cases and proved that they can effectively defend against various attacks because they actively cope with online fraud and obtain visibility of user accounts.

• Journal of Korean Library and Information Science Society
• /
• v.48 no.3
• /
• pp.113-130
• /
• 2017

The goal of this study is to propose the approaches to improve the voters' awareness by analyzing the voters' awareness on the fake news related to the elections and identifying the problems with the focus on the 19th Presidential Election. In accordance with the analysis on the data from 128 respondents (53 male and 75 female respondents), the 99.2% (127 respondents) of respondents had informations on elections mainly through broadcasting(77.2%), smart phone(70.9%), Internet(63.8%) and newspapers 32.3% which accounts for 41 respondents) in that sequence. Next, the 87.4% of respondents thought that the informations on elections had more impact on their voting than the generally expected degree. Meanwhile, the voters' awareness on the facts was analyzed by collecting and presenting the information on elections which stated by candidates in the 19th Presidential Election. In accordance with the analysis, there were the significant differences per age groups. The Scheffe test indicated that the respondents in 30s to 40s had significantly higher average awareness than those in 20s. According to the analysis results, it was proposed that the National Election Commission install the election information investigation and analysis committee in the election organization, investigate and analyze the election informations each election for providing real facts to the public, the voters.

• Journal of Dairy Science and Biotechnology
• /
• v.26 no.2
• /
• pp.9-22
• /
• 2008

This work has been conducted as a part to set up the regulations and the scientific evaluation systems for the functional dairy products with health claims in Korea. Toward this end, current regulations, requirements, and all kinds of provisions related to the functional dairy products overseas were taken into accounts and feasible recommendations of new initiatives on the current regulations as well. By doing so, not only protecting hopefully the innocent consumers from the false labeling statements and fake advertisements, but also eventually to revitalize the stagnated domestic dairy industries. Currently, functional daily products are simply regarded as "Dietary Supplements" in the United States, and subjected to the regulations under the Dietary Supplement Health and Education Act, established m 1994. Manufacturers and sales distributors should notify their products to the FDA, which is in charge of the dietary supplements on nutrition and labeling, in advance when they start marketing a new dietary ingredient or any foods containing it in the States. For EU countries, there exists keen interests about the functional food products between the member countries of the European Union even though the products are categorized into "Food Supplements" similar to those in the United States. Therefore, they maintain a cautious attitude in applying the health claims to the functional food products. On the other hand, under the Japanese health food system, functional foods are qualified to the functional health foods in terms of legal status as long as any traditional foods can meet the legal standards in its effectiveness, safety as well as quality, along with significant scientific evidences related to the products, thus categorized into "Foods for Specified Health Uses and "Foods with Nutrient Function Claims". Through this study, we may have some expectations and potential utilizations as follows: Legal regulations of dietary supplements especially for the dairy products will be implemented by the outcomes of this research and proposed a tentative amendment of functional ingredients for the sake of consumer protection from the false advertisements and overstatement labeling. Current regulations on the animal foods processing and advertisements will be amended and supplemented in order to revitalize the current downturn dairy sales and to harmonize the international Codex recommendations. The results obtained from this study will make the consumers a wise selection of the dairy products with health claims and be utilized for consumer education and advertisement of the functional products as well.