On February 7, 2005, the Federal Trade Commission reported that at least 10 million Americans are affected by identity (ID) theft each year[7]. The US Department of Justice defines identity theft as ”all types of crime in which someone wrongfully obtains and uses another person’s personal data in some way that involves fraud or deception, typically for economic gain[17].” ID thieves target any personal information they can get including social security numbers, bank account or credit card numbers, mother’s maiden name, drivers license numbers, financial account numbers and pins, and online account names and passwords[7], [17]. These criminals use many different methods to attack unsuspecting people, gaining information that they then use to pretend to be those people. In this paper we explain some of the methods used by ID thieves. We will focus on Phishing, a web-based social engineering method of extracting personal information for the purpose of assuming the identity of the unsuspecting. The government has stepped up legislation to help prosecute those caught engaging in identity theft, but we must do more through education and personal protection[17], [7], [4]. II. GOALS AND MOTIVATION

Identity Theft

In online discussion communities, users can interact and share information and opinions on a wide variety of topics. However, some users may create multiple identities, or sockpuppets, and engage in undesired behavior by deceiving others or manipulating discussions. In this work, we study sockpuppetry across nine discussion communities, and show that sockpuppets differ from ordinary users in terms of their posting behavior, linguistic traits, as well as social network structure. Sockpuppets tend to start fewer discussions, write shorter posts, use more personal pronouns such as ``I'', and have more clustered ego-networks. Further, pairs of sockpuppets controlled by the same individual are more likely to interact on the same discussion at the same time than pairs of ordinary users. Our analysis suggests a taxonomy of deceptive behavior in discussion communities. Pairs of sockpuppets can vary in their deceptiveness, i.e., whether they pretend to be different users, or their supportiveness, i.e., if they support arguments of other sockpuppets controlled by the same user. We apply these findings to a series of prediction tasks, notably, to identify whether a pair of accounts belongs to the same underlying user or not. Altogether, this work presents a data-driven view of deception in online discussion communities and paves the way towards the automatic detection of sockpuppets.

An Army of Me: Sockpuppets in Online Discussion Communities

Visualization-based analysis of gameplay data – A review of literature

As online games become popular and the boundary between virtual and real economies blurs, cheating in games has proliferated in volume and method. In this paper, we propose a framework for user behavior analysis for bot detection in online games. Specifically, we focus on party play which reflects the social activities among gamers: in a Massively Multi-user Online Role Playing Game (MMORPG), party play is a major activity that game bots exploit to keep their characters safe and facilitate the acquisition of cyber assets in a fashion very different from that of normal humans. Through a comprehensive statistical analysis of user behaviors in game activity logs, we establish threshold levels for the activities that allow us to identify game bots. Based on this, we also build a knowledge base of detection rules, which are generic. We apply our rule reasoner to AION, a popular online game serviced by NCsoft, Inc., a leading online game company based in Korea.

Online game bot detection based on party-play log analysis

Interesting, human-like opponents add to the entertainment value of a video game, and creating such opponents is a difficult challenge for programmers. Can artificial intelligence and computational intelligence provide the means to convincingly simulate a human opponent? Or are simple programming tricks and deceptions more effective? To answer these questions, the author designed and organised a game bot programming competition, the BotPrize, in which competitors submit bots that try to pass a “Turing Test for Bots”. In this paper, we describe a new design for the competition, which will make it simpler to run, and, we hope, open up new opportunities for innovative use of the testing platform. We illustrate the potential of the new platform by describing an implementation of a bot that is designed to learn how to appear more human using feedback obtained during play.

/pdf/a-new-design-for-a-turing-test-for-bots-51fh4s7x50.pdf

A new design for a Turing Test for Bots

Account hijacking is considered one of the most serious security problems in online games A hijacker normally takes away valuable virtual items from the stolen accounts, and trades those items for real money Even though account hijacking is not uncommon, there is currently no general solutions to determine whether an account has been hijacked The game company is not aware of a hijack unless it is reported by the victim However, it is usually too late---usually a hijacker already took away anything valuable when a user finds that his/her account has been stolenIn this paper, we propose a new biometric for human identification based on users' game-play activities Our main summary are two-fold: 1) we show that the idle time distribution is a representative feature of game players; 2) we propose the RET scheme, which is based on the KullbackLeibler divergence between idle time distributions, for user identification Our evaluations shows that the RET scheme achieves higher than 90% accuracy with a 20-minute detection time given a 200-minute history size

/pdf/user-identification-based-on-game-play-activity-patterns-432avld9e4.pdf

Li-Wen Hong

Papers

User identification based on game-play activity patterns