• Journal of Information Technology Applications and Management
• /
• v.25 no.1
• /
• pp.19-32
• /
• 2018

Fake news is defined as the news articles that are intentionally and verifiably false, and could mislead readers. Spread of fake news may provoke anxiety, chaos, fear, or irrational decisions of the public. Thus, detecting fake news and preventing its spread has become very important issue in our society. However, due to the huge amount of fake news produced every day, it is almost impossible to identify it by a human. Under this context, researchers have tried to develop automated fake news detection method using Artificial Intelligence techniques over the past years. But, unfortunately, there have been no prior studies proposed an automated fake news detection method for Korean news. In this study, we aim to detect Korean fake news using text mining and machine learning techniques. Our proposed method consists of two steps. In the first step, the news contents to be analyzed is convert to quantified values using various text mining techniques (Topic Modeling, TF-IDF, and so on). After that, in step 2, classifiers are trained using the values produced in step 1. As the classifiers, machine learning techniques such as multiple discriminant analysis, case based reasoning, artificial neural networks, and support vector machine can be applied. To validate the effectiveness of the proposed method, we collected 200 Korean news from Seoul National University's FactCheck (http://factcheck.snu.ac.kr). which provides with detailed analysis reports from about 20 media outlets and links to source documents for each case. Using this dataset, we will identify which text features are important as well as which classifiers are effective in detecting Korean fake news.

• The Journal of Society for e-Business Studies
• /
• v.23 no.4
• /
• pp.19-39
• /
• 2018

Recently, fake news has attracted worldwide attentions regardless of the fields. The Hyundai Research Institute estimated that the amount of fake news damage reached about 30.9 trillion won per year. The government is making efforts to develop artificial intelligence source technology to detect fake news such as holding "artificial intelligence R&D challenge" competition on the title of "searching for fake news." Fact checking services are also being provided in various private sector fields. Nevertheless, in academic fields, there are also many attempts have been conducted in detecting the fake news. Typically, there are different attempts in detecting fake news such as expert-based, collective intelligence-based, artificial intelligence-based, and semantic-based. However, the more accurate the fake news manipulation is, the more difficult it is to identify the authenticity of the news by analyzing the news itself. Furthermore, the accuracy of most fake news detection models tends to be overestimated. Therefore, in this study, we first propose a method to secure the fairness of false news detection model accuracy. Secondly, we propose a method to identify the authenticity of the news using the social data broadly generated by the reaction to the news as well as the contents of the news.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.4
• /
• pp.33-39
• /
• 2018

In this paper, we propose a describes how to detect a false iris image by inserting watermark into a iris image. The existing method, which inserts the watermark into the entire iris image to detect a fake iris, has a problem that can evade it by segmenting iris region of an iris image. The purpose of overcoming the problem, this paper proposes a new fake iris detection technique based on digital watermark. It first searches a central point of an iris image, divide the image into blocks with respect to the point. executes Discrete Cosine Transform, inserts watermark into the blocks, and then verifies an iris image using NC(Normalized Correlation). In the experiments, we confirm the robustness for attacks - crop and JPEG.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.627-630
• /
• 2022

Over the past few years, fake news has become one of the most significant problems. Since it is impossible to prevent people from spreading misinformation, people should analyze the news themselves. However, this process takes some time and effort, so the routine part of this analysis should be automated. There are many different approaches to this problem, but they only analyze the text and messages, ignoring the images. The fake news problem should be solved using a complex analysis tool to reach better performance. In this paper, we propose the approach of training an Artificial Intelligence using an unsupervised learning algorithm, combined with online data parsing tools, providing independence from subjective data set. Therefore it will be more difficult to spread fake news since people could quickly check if the news or article is trustworthy.

• Journal of Internet Computing and Services
• /
• v.21 no.2
• /
• pp.57-64
• /
• 2020

The widespread use of smartphones with a variety of features has enabled mobile Internet-based services. One of these is online-to-offline (O2O) based services that connects online users with offline stores to add value. Applying this O2O strategy to local information retrieval induces online users to be linked to offline regions, thereby enabling the exchange of local-based information and helps create new value. This paper proposes and illustrates the implementation of O2O-based a local information providing service that utilizes photos of the local attraction. Also, we propose a fake-free ranking method to provide reliable local information to users and suggest its application of the service.

• Journal of Digital Contents Society
• /
• v.19 no.1
• /
• pp.205-212
• /
• 2018

In this paper, we propose a method for more accurate fake discrimination using time information in CNN-based signature recognition. To easily use the time information and not to be influenced by the speed of signature writing, we acquire the signature as a movie and divide the total time of the signature into equal numbers of equally spaced intervals to obtain each image and synthesize them to create signature data. In order to compare the method using the proposed signature image and the method using only the last signature image, various signature recognition methods based on CNN have been experimented in this paper. As a result of experiment with 25 signature data, we found that the method using time information improves performance in fake discrimination compared to the existing method at all experiments.

• Journal of Korea Society of Industrial Information Systems
• /
• v.23 no.5
• /
• pp.9-17
• /
• 2018

Recently, the increasing interest of biometric systems has led to the creation of many researches of biometrics forgery. In order to solve this forgery problem, this paper proposes a method of determining whether a synthesized face made of artificaial intelligence is real face or fake face. The proposed algorithm consists of two steps. Firstly, we create the fake face images using various GAN (Generative Adversarial Networks) algorithms. After that, deep learning algorithm can classify the real face image and the generated face image. The experimental results shows that the proposed algorithm can detect the fake face image which looks like the real face. Also, we obtained the classification accuracy of 88.7%.

• Information Systems Review
• /
• v.23 no.4
• /
• pp.127-146
• /
• 2021

Fake news isexpanded and reproduced rapidly regardless of their authenticity by the characteristics of modern society, called the information age. Assuming that 1% of all news are fake news, the amount of economic costs is reported to about 30 trillion Korean won. This shows that the fake news isvery important social and economic issue. Therefore, this study aims to develop an automated detection model to quickly and accurately verify the authenticity of the news. To this end, this study crawled the news data whose authenticity is verified, and developed fake news prediction models using word embedding (Word2Vec, Fasttext) and deep learning algorithms (LSTM, BiLSTM). Experimental results show that the prediction model using BiLSTM with Word2Vec achieved the best accuracy of 84%.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.7C
• /
• pp.971-984
• /
• 2004

In the coming age of information warfare, information security patterns need to be changed such as to the active approach using offensive security mechanisms rather than traditional passive approach just protecting the intrusions. In an active security environment, it is essential that, when detecting an intrusion, the immediate confrontation such as analysing the intrusion situation in realtime, protecting information from the attacks, and even tracing the intruder. This paper presents an active intrusion-confronting system using a fake session and a honeypot. Through the fake session, the attacks like Dos(Denial of Service) and port scan can be intercepted. By monitoring honeypot system, in which the intruders are migrated from the protected system and an intrusion rule manager is being activated, new intrusion rules are created and activated for confronting the next intrusions.

• Korean Journal of Agricultural Science
• /
• v.49 no.3
• /
• pp.495-510
• /
• 2022

In this study, fluorescence hyperspectral imaging (FHSI) was used for the rapid, non-destructive detection of fake, manmade eggs from real eggs. To identify fake eggs, protoporphyrin IX (PpIX)-a natural pigment present in real eggshells-was utilized as the main indicator due to its strong fluorescence emission effect. The fluorescence images of real and fake eggs were acquired using a line-scan-based FHSI system, and their fluorescence features were analyzed based on spectroscopic techniques. To improve the detection performance and accuracy, an optimal waveband combination was investigated with analysis of variance (ANOVA), and its fluorescence ratio images (588/645 nm) were created for visualization of the real eggs between two different egg groups. In addition, real and fake eggs were scanned using a one-waveband (645 nm) handheld fluorescence imager that can perform real-time scanning for on-site applications. Then, the results of the two methods were compared with one another. The outcome clearly shows that the newly developed FHSI system and the fluorescence handheld imager were both able to distinguish real eggs from fake eggs. Consequently, FHSI showed a better performance (clearer images) compared to the fluorescence handheld imager, and the outcome provided valuable information about the feasibility of using FHSI imaging with ANOVA for the discrimination of real and fake eggs.