• Electronics and Telecommunications Trends
• /
• v.36 no.2
• /
• pp.75-82
• /
• 2021

Online action detection (OAD) in a streaming video is an attractive research area that has aroused interest lately. Although most studies for action understanding have considered action recognition in well-trimmed videos and offline temporal action detection in untrimmed videos, online action detection methods are required to monitor action occurrences in streaming videos. OAD predicts action probabilities for a current frame or frame sequence using a fixed-sized video segment, including past and current frames. In this article, we discuss deep learning-based OAD models. In addition, we investigated OAD evaluation methodologies, including benchmark datasets and performance measures, and compared the performances of the presented OAD models.

• Journal of Korea Game Society
• /
• v.15 no.4
• /
• pp.69-78
• /
• 2015

As the online game industry has been growing rapidly, more and more malicious activities to gain economic benefits have been reported as well. Game bot is one of the biggest problems in the online game industry. So we proposed a bot detection method based on the ERG theory of motivation for the first time. Most of the previous studies focused on behavior-based detection by monitoring patterns of the specific actions. In this paper, we applied the motivation theory to analyze user behaviors on a real game dataset. The result shows that normal users in the game followed the ERG theory of motivation in the same way as it works in real world. But in the case of game bots, the theory could not be applied because the game bot has specific reasons, unlike normal game users. We applied the ERG theory to users to distinguish game bot users from normal users. We detected the game bot with high accuracy of 99.78% by applying the theory.

• Review of KIISC
• /
• v.27 no.4
• /
• pp.14-21
• /
• 2017

온라인 게임은 가상 재화를 현금화할 수 있게 되면서 여러 가지 부정 행위가 발생하고 있다. 그 중 대표적인 것이 사용자 대신에 게임 플레이를 해주는 게임 봇(game bot)이다. 이러한 게임 봇은 사용자는 물론 게임회사에 큰 해를 입히고 있다. 본 연구에서는 게임 봇을 탐지하는 기존의 연구 중 사용자의 행동 로그를 분석하는, 데이터 분석 기반의 연구를 조사하였다. 관련 연구를 사용자의 행위를 중심으로 구분하였고, 향후 연구가 나아갈 방향에 대해 첨언하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.703-705
• /
• 2022

코로나19 대유행으로 비대면 교육이 보편화되어 온라인 학습과 시험이 교육기관에서 일반화되고 있다. 이러한 급격한 변화로 교육의 공정성 문제와 온라인 시험의 부정행위 문제가 대두되고 있다. 온라인 시험은 대면 시험과는 달리 시험 감독관이 부정행위를 적발하기 어렵기 때문에 응시자의 다양한 환경을 고려하여 정확하게 부정행위를 판별하는 방법이 필요하다. 본 연구에서는 온라인 시험환경에서 응시자의 행동 데이터와 영상데이터를 분석하여 부정행위를 감독관에게 추천하는 시스템을 제안한다. 제안 시스템의 구현을 통해 온라인 시험 환경에서 부정행위를 탐지 기능을 확인한다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.22 no.2
• /
• pp.225-238
• /
• 2012

Among the various security threats in online games, the use of game bots is the most serious problem. In this paper, we propose a framework for user behavior analysis for bot detection in online games. Specifically, we focus on party play that reflects the social activities of gamers: In a Massively Multi-user Online Role Playing Game (MMORPG), party play log includes a distinguished information that can classify game users under normal-user and abnormal-user. That is because the bot users' main activities target on the acquisition of cyber assets. Through a statistical analysis of user behaviors in game activity logs, we establish the threshold levels of the activities that allow us to identify game bots. Also, we build a knowledge base of detection rules based on this statistical analysis. We apply these rule reasoner to the sixth most popular online game in the world. As a result, we can detect game bot users with a high accuracy rate of 95.92%.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.9
• /
• pp.4200-4206
• /
• 2012

Recently, online-game industry has been rapidly expanding in these days. But, the various game service victimized cases are generated by the bots program. Particularly, the abnormal collection of the game money and item loses the inherent fun of a game. It reaches ultimately the definite bad effect to the game life cycle. In this paper, we propose a Bots detection method by observing the playing patterns of game characters with game log data. It analyzed behaviors of human players as well as bots and identified features to build the model to differentiate bots from human players. In an experiment, by using the served online-game, the model of a user and bots were generated was distinguished. And the reasonable result was confirmed.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.25 no.3
• /
• pp.627-637
• /
• 2015

As game item trading becomes more popular with the rapid growth of online game market, the market for trading game items by cash has increased up to KRW 1.6 trillion. Thanks to this active market, it has been easy to turn these items and game money into real money. As a result, some malicious users have often attempted to steal other players' rare and valuable game items by using their account. Therefore, this study proposes a detection model through analysis on these account thieves' behavior in the Massive Multiuser Online Role Playing Game(MMORPG). In case of online game identity theft, the thieves engage in economic activities only with a goal of stealing game items and game money. In this pattern are found particular sequences such as item production, item sales and acquisition of game money. Based on this pattern, this study proposes a detection model. This detection model-based classification revealed 86 percent of accuracy. In addition, trading patterns when online game identity was stolen were analyzed in this study.

• Knowledge Management Research
• /
• v.21 no.3
• /
• pp.177-195
• /
• 2020

The social consciousness on fake reviews has triggered researchers to suggest ways to cope with them by analyzing contents of fake reviews or finding ways to discover them by means of structural characteristics of them. This research tried to collect data from blog posts in Naver and detect habitual patterns users use unconsciously by variables extracted from blogs and blog posts by a machine learning model and wanted to use the technique in predicting fake reviews. Data analysis showed that there was a very high relationship between the number of all the posts registered in the blog of the writer of the related writing and the date when it was registered. And, it was found that, as model to detect advertising reviews, Random Forest is the most suitable. If a review is predicted to be an advertising one by the model suggested in this research, it is very likely that it is fake review, and that it violates the guidelines on investigation into markings and advertising regarding recommendation and guarantee in the Law of Marking and Advertising. The fact that, instead of using analysis of morphemes in contents of writings, this research adopts behavior analysis of the writer, and, based on such an approach, collects characteristic data of blogs and blog posts not by manual works, but by automated system, and discerns whether a certain writing is advertising or not is expected to have positive effects on improving efficiency and effectiveness in detecting fake reviews.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.3
• /
• pp.422-427
• /
• 2010

Korean Game industry, especially MMORPG(Massively Multiplayer Online Game) has been rapidly expanding in these days. But As game industry is growing, lots of online game security incidents have also been increasing and getting prevailing. One of the most critical security incidents is 'Game Bots', which are programs to play MMORPG instead of human players. If player let the game bots play for them, they can get a lot of benefic game elements (experience points, items, etc.) without any effort, and it is considered unfair to other players. Plenty of game companies try to prevent bots, but it does not work well. In this paper, we propose a behavior pattern model for detecting bots. We analyzed behaviors of human players as well as bots and identified six game features to build the model to differentiate game bots from human players. Based on these features, we made a Naive Bayesian classifier to reasoning the game bot or not. To evaluated our method, we used 10 game bot data and 6 human Player data. As a result, we classify Game bot and human player with 88% accuracy.