• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.1825-1844
• /
• 2019

Political campaigns circulate manipulative opinions in online communities to implant false beliefs and eventually win elections. Not only is this type of manipulation unfair, it also has long-lasting negative impacts on people's lives. Existing tools detect political manipulation based on a supervised classifier, which is accurate when trained with large labeled data. However, preparing this data becomes an excessive burden and must be repeated often to reflect changing manipulation tactics. We propose a practical detection system that requires moderate groundwork to achieve a sufficient level of accuracy. The proposed system groups opinions with similar properties into clusters, and then labels a few opinions from each cluster to build a classifier. It also models each opinion with features deduced from raw data with no additional processing. To validate the system, we collected over a million opinions during three nation-wide campaigns in South Korea. The system reduced groundwork from 200K to nearly 200 labeling tasks, and correctly identified over 90% of manipulative opinions. The system also effectively identified transitions in manipulative tactics over time. We suggest that online communities perform periodic audits using the proposed system to highlight manipulative opinions and emerging tactics.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1671-1686
• /
• 2022

Face manipulation tools represented by Deepfake have threatened the security of people's biological identity information. Particularly, manipulation tools with deep learning technology have brought great challenges to Deepfake detection. There are many solutions for Deepfake detection based on traditional machine learning and advanced deep learning. However, those solutions of detectors almost have problems of poor performance when evaluated on different quality datasets. In this paper, for the sake of making high-quality Deepfake datasets, we provide a preprocessing method based on the image pixel matrix feature to eliminate similar images and the residual channel attention network (RCAN) to resize the scale of images. Significantly, we also describe a Deepfake detector named Cascaded-Hop which is based on the PixelHop++ system and the successive subspace learning (SSL) model. By feeding the preprocessed datasets, Cascaded-Hop achieves a good classification result on different manipulation types and multiple quality datasets. According to the experiment on FaceForensics++ and Celeb-DF, the AUC (area under curve) results of our proposed methods are comparable to the state-of-the-art models.

• The Korean Journal of Applied Statistics
• /
• v.29 no.5
• /
• pp.907-920
• /
• 2016

This study suggests an outlier detection algorithm that uses quantile autoregressive model in time series data, eventually applying it to actual stock manipulation cases by comparing its performance to existing methods. Studies on outlier detection have traditionally been conducted mostly in general data and those in time series data are insufficient. They have also been limited to a parametric model, which is not convenient as it is complicated with an analysis that takes a long time. Thus, we suggest a new algorithm of outlier detection in time series data and through various simulations, compare it to existing algorithms. Especially, the outlier detection algorithm in time series data can be useful in finding stock manipulation. If stock price which had a certain pattern goes out of flow and generates an outlier, it can be due to intentional intervention and manipulation. We examined how fast the model can detect stock manipulations by applying it to actual stock manipulation cases.

• MALSORI
• /
• no.60
• /
• pp.97-108
• /
• 2006

The purpose of this study is to observe how Korean listeners detect a target phoneme with 'Focus' represented by prosodic prominence and question-induced semantic emphasis, and with intonational manipulation. According to the automated phoneme detection task using E-Prime, the Korean listeners detected phoneme targets more rapidly when the target-bearing words were in prominence position and in question-induced position. However, the presence of question-induced semantic emphasis reduced the prominence effect, so two effects interacted: when question-induced emphasis were primarily given as a cue, prominence which was given as secondary cue affected less to fine the new information. Besides, the intonation with manipulation was responded to faster than without manipulation.

• Proceedings of the Optical Society of Korea Conference
• /
• 2007.07a
• /
• pp.33-34
• /
• 2007

• Proceedings of the Korean Magnestics Society Conference
• /
• 2008.12a
• /
• pp.18.1-18.1
• /
• 2008

• Journal of Intelligence and Information Systems
• /
• v.12 no.4
• /
• pp.15-37
• /
• 2006

In this paper, we discuss a data mining approach to detection of stock price manipulation in the Korean stock market. First of all, we review current methods which is being exercised in the Korean stock market as well as in the US stock market. And then we apply data mining techniques to the problem using data from the Korean stock market and discuss the results along with their implications.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.540-542
• /
• 2023

Due to the serious issues posed by facial manipulation technologies, many researchers are becoming increasingly interested in the identification of face forgeries. The majority of existing face forgery detection methods leverage powerful data adaptation ability of neural network to derive distinguishing traits. These deep learning-based detection methods frequently treat the detection of fake faces as a binary classification problem and employ softmax loss to track CNN network training. However, acquired traits observed by softmax loss are insufficient for discriminating. To get over these limitations, in this study, we introduce a novel discriminative feature learning based on Vision Transformer architecture. Additionally, a separation-center loss is created to simply compress intra-class variation of original faces while enhancing inter-class differences in the embedding space.

• Science of Emotion and Sensibility
• /
• v.16 no.3
• /
• pp.341-350
• /
• 2013

The present study aimed to understand the sensory characteristic of change detection by comparing the experience of detecting a salient visual change against the experience of detecting a sensory conflict evoked by a binocular mismatch. In Experiment 1, we used the change detection task where 2, 4, or 6 items were short-term remembered in visual working memory and were compared with following test items. The half of change-present trials were manipulated to elicit a binocular rivalry on the test item with the change by way of monocular inputs across the eyes. The results showed that change detection accuracy without the rivalry manipulation declined evidently as the display setsize increased whereas no such setsize effect was observed with the rivalry manipulation. Experiment 2 tested search efficiency for the search array where the target was designated as an item with the rivalry manipulation, and found the search was very efficient regardless of the rivalry manipulation. The results of Experiment 1 and 2 showed that when the given memory load varies, the experience of detecting a salient visual change become similar to the experience of detecting a sensory conflict by a binocular rivalry.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.4
• /
• pp.671-685
• /
• 2023

By applying artificial intelligence to image editing technology, it has become possible to generate high-quality images with minimal traces of manipulation. However, since these technologies can be misused for criminal activities such as dissemination of false information, destruction of evidence, and denial of facts, it is crucial to implement strong countermeasures. In this study, image file and mobile forensic artifacts analysis were conducted for detecting image manipulation. Image file analysis involves parsing the metadata of manipulated images and comparing them with a Reference DB to detect manipulation. The Reference DB is a database that collects manipulation-related traces left in image metadata, which serves as a criterion for detecting image manipulation. In the mobile forensic artifacts analysis, packages related to image editing tools were extracted and analyzed to aid the detection of image manipulation. The proposed methodology overcomes the limitations of existing graphic feature-based analysis and combines with image processing techniques, providing the advantage of reducing false positives. The research results demonstrate the significant role of such methodology in digital forensic investigation and analysis. Additionally, We provide the code for parsing image metadata and the Reference DB along with the dataset of manipulated images, aiming to contribute to related research.