Search

We consider a binary labelling problem: for some machine learning applications, two types of distinct objects are required to be labeled respectively, before a classifier can be trained. We show that the famous ESP game and variants would not work well on this binary labelling problem. We discuss how to design a new human computation game to solve this problem. It turns out that interesting but subtle security issues emerge in the new game. We introduce novel gaming mechanisms, such as ‘guess disagreement’, which improve the game’s security, usability and productivity simultaneously.

First Person Shooter (FPS) is a popular genre in online gaming, unfortunately not everyone plays the game fairly, and this hinders the growth of the industry. The aiming robot (aimbot) is a common cheating mechanism employed in this genre, it differs from many other common online bots in that there is a human operating alongside the bot, and thus the in-game data exhibit both human and bot-like behaviour. The aimbot users can aim much better than the average player. However, there are also a large number of highly skilled players who can aim much better than the average player, some of these players have in the past been banned from servers due to false accusations from their peers. Therefore, it would be interesting to find out if and where the honest player's and the bot user's behaviour differ. In this paper we investigate the difference between the aiming abilities of aimbot users and honest human players. We introduce two novel features and have conducted an experiment using a modified open source FPS game. Our data shows that there is significant difference between behaviours of honest players and aimbot users. We propose a voting scheme to improve aimbot detection in FPS based on distribution matching, and have achieved approximately 93% in both True positive and True negative rates with one of our features.

Online gaming is very popular and has gained some recognition as the so called e-sport over the last decade. However, in particular First Person Shooter (FPS) games suffer from the development of sophisticated cheating methods such as aiming robots (aimbot), which can boost the players ability to acquire and track targets by the illicit use of internal game states. This not only gives an obvious unfair advantage to the cheater, but has negative impact on the gaming experience of honest players. In this paper we present a novel supervised method based on distribution comparison matrices that shows very promising performance in the identification of players that use such aimbots. It extends our previous work in which two features were identified and shown to have good predictive performance. The proposed method is further compared with other classification techniques such as Support Vector Machines (SVM). Overall we achieve true positive and true negatives rates well above 98% with low computational requirements.

In this demo, we showcase Magic Bullet, an online game that is designed to streamline the robustness evaluation of CAPTCHAs. This game can also train people's typing skills, and be used to aid the development of better machine learning algorithms for handwriting recognition.

CAPTCHA has been widely deployed by commercial web sites as a security technology for purposes such as anti-spam. A common approach to evaluating the robustness of CAPTCHA is the use of machine learning techniques. Critical to this approach is the acquisition of an adequate set of labeled samples, on which the learning techniques are trained. However, such a sample labeling task is difficult for computers, since the strength of CAPTCHAs stems exactly from the difficulty computers have in recognizing either distorted texts or image contents. Therefore, until now, researchers have to manually label their samples, which is tedious and expensive. In this paper, we present Magic Bullet, a computer game that for the first time turns such sample labeling into a fun experience, and that achieves a labeling accuracy of as high as 98% for free. The game leverages human computation to address a task that cannot be easily automated, and it effectively streamlines the evaluation of CAPTCHAs. The game can also be used for other constructive purposes such as 1) developing better machine learning algorithms for handwriting recognition, and 2) training people's typing skills.