자기 유사도를 이용한 MMORPG 게임봇 탐지 시스템

국문 초록 (Abstract)

다중 접속 역할 게임(Massively Multi-Online Role Playing Game, MMORPG)에서 게임봇은 게임 밸런스에 악영향을 끼치고 일반 유저들에게 상대적인 박탈감을 느끼게 하여 게임 수명을 단축시키는 위험 요소이다. 따라서 그 동안 게임 봇을 탐지하기 위한 다양한 방법이 연구되었으나 특정 게임 컨텐츠의 특징에 초점을 맞춤에 따라 신규 게임이 출시될 때마다 탐지 기법 개발이 필요하거나 혹은 게임 및 봇 프로그램 업데이트에 따른 유지 보수 방안을 고려하지 않고 있다. 본 논문에서는 게임봇이 본질적으로 갖고 있는 특징인, 설정된 패턴에 따라 행동을 반복하는 자기유사성을 주요 특질로 이용한 기계 학습 기법을 제안하고 이렇게 학습한 모델을 자동으로 유지 보수하는 시스템을 제안하였다. 이렇게 제안한 방법은 엔씨소프트의 대표 MMORPG인 리니지, 아이온, 블레이드 앤 소울에 대해 성능을 테스트하였으며 시스템을 구현하여 실전에 적용하였다.

다국어 초록 (Multilingual Abstract)

Game bot playing is one of the main risks in Massively Multi-Online Role Playing Games(MMORPG) because it damages overall game playing environment, especially the balance of the in-game economy. There have been many studies to detect game bot. However, the previous detection models require continuous maintenance efforts to train and learn the game bots’ patterns whenever the game contents change. In this work, we have proposed a machine learning technique using the self-similarity property that is an intrinsic attribute in game bots and automated maintenance system. We have tested our method and implemented a system to major three commercial games in South Korea. As a result, our proposed system can detect and classify game bots with high accuracy.

목차 (Table of Contents)

• 요약
• ABSTRACT
• Ⅰ. Introduction
• Ⅱ. Related Works
• Ⅲ. Self-similarity of Game Bots
• Ⅳ. Methodology
• Ⅴ. Experiments
• Ⅵ. Conclusion
• Ⅶ. Future Works
• References

참고문헌 (Reference)

1 Woo, K, "What can Free Money Tell Us on the Virtual Black Market" 41 (41): 392-393, 2011

2 Roy, A, "The Ones That Got Away : False Negative Estimation Based Approaches for Gold Farmer Detection" 328-337, 2012

3 Hunter, J. S, "The Exponentially Weighted Moving Average" 18 (18): 203-210, 1986

4 Kwon, K, "Surgical Strike : A Novel Approach to Minimize Collateral Damage to Game Bot Detection" 1-2, 2013

5 Crovella, M.E, "Selfsimilarity in World Wide Web traffic : evidence and possible causes" 5 (5): 835-846, 1997

6 Kwon, H, "Self-similarity Based Bot Detection System in MMORPG" 2011

7 Kang, A, "Online Game Bot Detection Based on Party-Play Log Analysis" 65 (65): 1384-1395, 2013

8 Ahmad, M.A, "Mining for Gold Farmers: Automatic Detection of Deviant Players in MMOGS" 4 : 340-345, 2009

9 Kwon, H, "Intelligent Information and Database Systems" Springer 353-362, 2011

10 Chen, K, "Game Bot Detection Based on Avatar Trajectory" 5309 : 94-105, 2009

11 정연오, "Game Bot Detection Approach Based on Behavior Analysis and Consideration of Various Play Styles" 한국전자통신연구원 35 (35): 1058-1067, 2013

12 Thawonmas, R, "Detection of MMORPG Bots Based on Behavior Analysis" 91-94, 2008

13 Lee, E, "Detecting the Bank Character in MMORPGs by Analysis of a Clustered Network" 2011

14 Fujita, A, "Detecting Real Money Traders in MMORPG by Using Trading Network" 2011

15 Keegan, B, "Dark Gold : Statistical Properties of Clandestine Networks in Massively Multiplayer Online Games" 201-208, 2010

16 강아름, "Chatting Pattern Based Game BOT Detection: Do They Talk Like Us?" 한국인터넷정보학회 6 (6): 2866-2879, 2012

17 Cevizci, I, "Analysis of Multi-Player Online Game Traffic Based on Self-similarity" 2006

18 Kesteren, M, "A Step in the Right Detection : Bot Detection in MMORPGs using Movement Analysis" 2009