Player authentication is important to ensure fairness in esports, and fighting games present a particularly challenging setting because of their discrete and limited input modalities and rapidly changing gameplay situations. While prior work has demonstrated the feasibility of controller-operation-based authentication in this domain, it has evaluated the approach only on a single title, leaving the empirical basis for this line of research still narrow. In this paper, using replay data from GUILTY GEAR -STRIVE-, we present a method for constructing a dataset for player authentication, which integrates three types of information: controller operation logs, battle progression, and battle attributes. To demonstrate its utility, we apply an existing controller-operation-based authentication method and show that the dataset supports the evaluation of such methods. We also analyze the relationship between player proficiency and authentication performance, and show that authentication tends to become more difficult as player proficiency increases. Our results show replay-derived data are practical for evaluating and analyzing player authentication in fighting games.

As one of the largest entertainment sectors globally, the gaming industry has already surpassed the music industry in revenue and is expected to continue its steady growth in the years ahead. Beyond leisure, gaming has become a competitive arena, particularly with the rise of esports, where games like CounterStrike (CS) draws millions of players and viewers worldwide. With the expansion of online gaming and virtual environments, new security challenges emerge that require advanced solutions. One promising approach is biometric identification based on ingame behavioral data, which is non-invasive and challenging to replicate. Although research has demonstrated effective player identification in Virtual Reality and turn-based games like chess, games like$C S$introduce unique challenges due to their dynamic high-speed interactions. This study explores behavioral biometrics to identify esports players based on their in-game behaviors. We use a multiclass Random Forest Classifier to analyze in-game movement, positioning, and weapon choices to identify individual players accurately. Our models achieve up to 98 % accuracy based on a combined dataset of 360 players across 320 matches. This data is divided into eight separate datasets for each map. These findings contribute to behavior-based player biometrics and identification, with applications in player analytics, team strategy optimization, and security in competitive gaming.

Smartphones have become more ubiquitous than ever. People are installing various applications on their smart-phone to fit into their lifestyle. Existing research shows that there are patterns within the ways people access those applications, whether it involves particular locations, particular ranges of time, or many other factors. In this research, through a collaboration with a commercial company, we collected usage data from a popular smartphone application that gives its users access to digital flyers information for shops and supermarkets throughout Japan. Our early experiments found that the pattern information contained inside the data could be used to authenticate users. In this research, we are proposing a behavioral authentication model implementing customized learning classifier systems to search through vast amount of possible patterns to authenticate users of the application. Our early findings for this ongoing research demonstrate that our model can feasibly be a good alternative for additional authentication factor to implicitly authenticate users beyond the initial registration.

Recently, information security has attracted more interest from researchers. Personal authentication has become more important than ever, because authentication vulnerability is regarded as a problem. In cases where such high confidentiality is required, multi-factor authentication which combines multiple authentication factors is often used. In this study, we focus on score fusion method which merge authentication score of each factor in multi-factor authentication. In conventional score fusion methods, the weighting of factors is fixed. Therefore, they are not suitable when the tendency for factors of high accuracy is different between users. We propose a user dependent weighting score fusion method using neural network. Our proposed method is evaluated in comparison with conventional score fusion methods. The result shows that the accuracy of our proposed method is higher than conventional methods.

In the area of intelligent systems, research about recommender systems is a critical topic and has been applied in many fields. In this paper, we focus on TV program recommender systems. We give an overview of literature research about TV program recommender systems and propose a smart and social TV program recommender framework for Smart TV, which integrates the Internet and Web 2.0 features into television sets and set-top boxes. In addition, we also address several issues, such as accuracy, diversity, novelty, explanation and group recommendations, which are important in building a TV program recommender system. The proposed framework could be used to help designers/developers to build TV program recommender systems/engines for smart TV.