Game Bots Research Articles

온라인게임산업 활성화 방안에 관한 연구

The purpose of this study is to derive efficient measures for revitalizing the online game market through prior studies related to existing online games, and to provide basic data for follow-up research related to the online game industry based on the current status of online games in Korea and empirical analysis. The literature analysis of previous studies suggested the following activation measures. First, user churn is one of the important problems in the online game industry, and it is necessary to develop and apply a new churn prediction model to prevent it. Second, since the number of cases of using game bots to obtain economic benefits is increasing, a detection technique using motivation-based ERG theory is needed as a strategy to detect and prevent them. Third, the government should create an environment that provides opportunities to solve various online game-related problems autonomously. Fourth, Efforts should be made to leverage the OSMU strategy to provide new experiences. Fifth, gaming companies need to create new business opportunities to expand the market, such as developing the amateur e-sports market.

Quick and easy game bot detection based on action time interval estimation

AbstractGame bots are illegal programs that facilitate account growth and goods acquisition through continuous and automatic play. Early detection is required to minimize the damage caused by evolving game bots. In this study, we propose a game bot detection method based on action time intervals (ATIs). We observe the actions of the bots in a game and identify the most frequently occurring actions. We extract the frequency, ATI average, and ATI standard deviation for each identified action, which is to used as machine learning features. Furthermore, we measure the performance using actual logs of the Aion game to verify the validity of the proposed method. The accuracy and precision of the proposed method are 97% and 100%, respectively. Results show that the game bots can be detected early because the proposed method performs well using only data from a single day, which shows similar performance with those proposed in a previous study using the same dataset. The detection performance of the model is maintained even after 2 months of training without any revision process.

Trading Behind-the-Scene: Analysis of Online Gold Farming Network in the Auction House System

Owing to the widespread use of smartphones, various online games based on mobile platforms are being launched. Although mobile games have the advantage of better accessibility compared to PC games, there is a limitation in that it is difficult to input specific actions. To overcome this limitation, game companies apply autoplay systems to support users. Autoplay (with macro or game bot programs) without human interaction was previously regarded as a cheating play. To provide a more comfortable and easy gaming experience to users, most mobile games currently provide autoplay functionality. Such introduction means that along with gold farming groups (GFGs), all users can use a game bot. Therefore, game companies prevent profit-producing activities of GFGs by introducing an in-game economic system in which a real money trading (RMT) is impossible. However, GFGs still operate by abusing an auction house. Our study uses the three-month transaction logs of a mobile game that introduces an auction house as an in-game economic system. We observe the abuse that makes RMTs possible through the auction house and propose a method of identifying abuse solely through a transaction log. We analyzed the GFGs using the identified abuse and confirmed that the GFG consists of a single role.

Effective Bots’ Detection for Online Smartphone Game Using Multilayer Perceptron Neural Networks

Online smartphone game bots can cause unfair behaviors and even shorten the game’s life cycle. The random forest algorithm in machine learning is a widely used solution to identify game bots through behavioral features. Although the random forest algorithm can exactly detect more definite game bot players, some players belonging to the gray area cannot be detected accurately. Therefore, this study collects players’ data and extracts the features to build the multilayer perceptron, neural network model, for effectively detecting online smartphone game bots. This approach calculates each player’s abnormal rate to judge game bots and is evaluated on the famous mobile online game. Based on these abnormal rates, we then use K means to cluster players and further define the gray area. In the experimental evaluation, the results demonstrate the proposed learning model has better performance, not only increasing the accuracy but also reducing the error rate as compared with the random forest model in the same players’ dataset. Accordingly, the proposed learning model can detect bot players more accurately and is feasible for real online smartphone games.

Controlling Unreal Tournament 2004 Bots with the Logic-Based Action Language GOLOG

Computer games and the accompanying entertainment industry branch has become a major market factor. AI techniques are successfully applied to tasks like path planning or intelligent swarm behavior. On the decision-making level the state of the art are state machines with a xed set of behaviors. The perception of the computer player is perfect. They exactly know where the other players are located, even if they cannot see them. This approach seems to be limited for intelligent decision making. Therefore, we propose another approach. We use a variant of the logic-based action language GOLOG for implementing so-called game bots in the UNREAL TOURNAMENT 2004 environment. First results show that we can compete with the omniscience game bots in the Unreal domain.

Hierarchical Plan Representations for Encoding Strategic Game AI

In this paper we explore the use of Hierarchical-Task-Network (HTN) representations to model strategic game AI. We will present two case studies. The first one reports on an experiment using HTNs to model strategies for Unreal Tournament® (UT) bots. We will argue that it is possible to encode strategies that coordinate teams of bots in first-person shooter games using HTNs. The second one compares an alternative to HTNs called Task-Method-Knowledge (TMK) process models. TMK models are of interest to game AI because, as we will show, they are as expressive as HTNs but have more convenient syntax. Therefore, HTN planners can be used to generate correct plans for coordinated team AI behavior modeled with TMK representations.

머신러닝을 이용한 누적 로그 기반 온라인 게임 봇 탐지 시스템

The online game market is steadily growing, and as such, there are active financial transactions to buy and sell game items. This paper focuses on developing an intelligent game bot detection system based on machine learning to detect game bots that collect game experience values and items illegally in online games. The proposed research method was constructed by reducing the learning data dimension using big data log information from RPG, AION games provided by KISA"s “K-Cyber Security Challenge” for intelligent game bot detection, and experiments were conducted using XgBoost and Random Forest models. Experiments show that the game bot detection performance of the proposed method with 97.7% of the results using a total of 3,761 account logs through visualization through correlation coefficient analysis of the data set accumulated with log information. The proposed research is currently applicable to the RPG (Role Playing Game) game bot detection field as a game bot detection method using machine learning technology.

Learning Human Motion Models

My research is focused on using human navigation data ingames and simulation to learn motion models from trajectorydata. These motion models can be used to: 1) track the opponent’smovement during periods of network occlusion; 2)learn combat tactics by demonstration; 3) guide the planningprocess when the goal is to intercept the opponent. A trainingset of example motion trajectories is used to learn twotypes of parameterized models: 1) a second order dynamicalsteering model or 2) the reward vector for a Markov DecisionProcess. Candidate paths from the model serve as themotion model in a set of particle filters for predicting the opponent’slocation at different time horizons. Incorporating theproposed motion models into game bots allows them to customizestheir tactics for specific human players and functionas more capable teammates and adversaries.

Living systems are smarter bots: Slime mold semiosis versus AI symbol manipulation

Although machines may be good at mimicking, they are not currently able, as organisms are, to act creatively. We offer an understanding of the emergent qualities of biological sign processing in terms of generalization, association, and encryption. We use slime mold as a model of minimal cognition and compare it to deep-learning video game bots, which some claim have evolved beyond their merely quantitative algorithms. We find that these discrete Turing machine bots are not able to make productive, yet unanticipated, "errors"-necessary for biological learning-which, based on the physicality of signs, their relatively similar shapes, and relative physical positions spatially and temporally, lead to emergent effects and make learning and evolution possible. In organisms, stochastic resonance at the local level can be leveraged for self-organization at the global level. We contrast all this to the symbolic processing of today's machine learning, whereby each logic node and memory state is discrete. Computer codes are produced by external operators, whereas biological symbols are evolved through an internal encryption process.

Improved Mitigation of Cyber Threats in IIoT for Smart Cities: A New-Era Approach and Scheme.

Cybersecurity in Industrial Internet of Things (IIoT) has become critical as smart cities are becoming increasingly linked to industrial control systems (ICSs) used in critical infrastructure. Consequently, data-driven security systems for analyzing massive amounts of data generated by smart cities have become essential. A representative method for analyzing large-scale data is the game bot detection approach used in massively multiplayer online role-playing games. We reviewed the literature on bot detection methods to extend the anomaly detection approaches used in bot detection schemes to IIoT fields. Finally, we proposed a process wherein the data envelopment analysis (DEA) model was applied to identify features for efficiently detecting anomalous behavior in smart cities. Experimental results using random forest show that our extracted features based on a game bot can achieve an average F1-score of 0.99903 using 10-fold validation. We confirmed the applicability of the analyzed game-industry methodology to other fields and trained a random forest on the high-efficiency features identified by applying a DEA, obtaining an F1-score of 0.997 using the validation set approach. In this study, an anomaly detection method for analyzing massive smart city data based on a game industry methodology was presented and applied to the ICS dataset.

Polygames: Improved zero learning

Since DeepMind’s AlphaZero, Zero learning quickly became the state-of-the-art method for many board games. It can be improved using a fully convolutional structure (no fully connected layer). Using such an architecture plus global pooling, we can create bots independent of the board size. The training can be made more robust by keeping track of the best checkpoints during the training and by training against them. Using these features, we release Polygames, our framework for Zero learning, with its library of games and its checkpoints. We won against strong humans at the game of Hex in 19 × 19, including the human player with the best ELO rank on LittleGolem; we incidentally also won against another Zero implementation, which was weaker than humans: in a discussion on LittleGolem, Hex19 was said to be intractable for zero learning. We also won in Havannah with size 8: win against the strongest player, namely Eobllor, with excellent opening moves. We also won several first places at the TAAI 2019 competitions and had positive results against strong bots in various games.

Adaptive Rehabilitation Bots in Serious Games.

In recent years, we have witnessed a growing adoption of serious games in telerehabilitation by taking advantage of advanced multimedia technologies such as motion capture and virtual reality devices. Current serious game solutions for telerehabilitation suffer form lack of personalization and adaptiveness to patients’ needs and performance. This paper introduces “RehaBot”, a framework for adaptive generation of personalized serious games in the context of remote rehabilitation, using 3D motion tracking and virtual reality environments. A personalized and versatile gaming platform with embedded virtual assistants, called “Rehab bots”, is created. Utilizing these rehab bots, all workout session scenes will include a guide with various sets of motions to direct patients towards performing the prescribed exercises correctly. Furthermore, the rehab bots employ a robust technique to adjust the workout difficulty level in real-time to match the patients’ performance. This technique correlates and matches the patterns of the precalculated motions with patients’ motions to produce a highly engaging gamified workout experience. Moreover, multimodal insights are passed to the users pointing out the joints that did not perform as anticipated along with suggestions to improve the current performance. A clinical study was conducted on patients dealing with chronic neck pain to prove the usability and effectiveness of our adjunctive online physiotherapy solution. Ten participants used the serious gaming platform, while four participants performed the traditional procedure with an active program for neck pain relief, for two weeks (10 min, 10 sessions/2 weeks). Feasibility and user experience measures were collected, and the results of experiments show that patients found our game-based adaptive solution engaging and effective, and most of them could achieve high accuracy in performing the personalized prescribed therapies.

NGUARD+

Game bots are automated programs that assist cheating users, leading to an imbalance in the game ecosystem and the collapse of user interest. Online games provide immersive gaming experience and attract many loyal fans. However, game bots have proliferated in volume and method, evolving with the real-world detection methods and showing strong diversity, leaving game bot detection efforts extremely difficult. Existing game bot detection techniques mostly rely on handcrafted features or time-series based features instead of fully utilizing player behavior sequences. In this regard, a more reasonable way should be learning user patterns from player behavior sequences when facing the fast-changing nature of game bots. Here we propose a general game bot detection framework for massively multiplayer online role playing games termed NGUARD+ (denoting NetEase Games’ Guard), which captures user patterns in order to identify game bots from player behavior sequences. NGUARD+ mainly employs attention-based methods to automatically differentiate game bots from humans. We provide a combination of supervised and unsupervised methods for game bot detection to detect game bots and new type of game bots even when the labels of game bots are limited. Specifically, we propose the following two variants for attention-based sequence modeling: Attention based Bidirectional Long Short-Term Memory Networks (ABLSTM) and Hierarchical Self-Attention Network (HSAN) as our supervised models. ABLSTM is keen on inducing certain inductive biases which makes learning more reasonable as well as capturing local dependency and global information, while HSAN could handle much longer behavior sequences with less memory and higher computational efficiency. Experiments conducted on a real-world dataset show that NGUARD+ can achieve remarkable performance improvement compared to traditional methods. Moreover, NGUARD+ can reveal outstanding robustness for game bots in mutated patterns and even in completely unseen patterns.

New biostatistics features for detecting web bot activity on web applications

Abstract Web bots are malicious scripts that automatically traverse the websites, fill the web form and illegally scrap the data from web sites. The never-ending threat of web bot is causing serious problems on the web applications. According to various web bot traffic reports, more than fifty percent of the total web traffic is coming from web bots. An effective safeguard against automated web bots is to detect the human user presence on the web applications. Most part of the existing research is focused on specific web bot detection such as form spamming bot, data scrapping bots, chat bots, and game bots. In this paper, the web bot detection model is proposed using combined supervised and unsupervised machine learning algorithms. In this paper, new Biostatistics features are proposed which is used to identify the human user presence on web applications. The Biostatistics features have proven very effective in discriminating human users from general web bots. Various attack scenarios are created for web bot attacks such as automated account registration, automatic form filling, and data scrapping to mimic the zero-day web bot attacks. The proposed model is evaluated by numerous experiments using standard evaluation parameters. The result analysis reveals that the proposed model is efficient in discriminating human users from web bots.

Efficient Deep Learning Bot Detection in Games Using Time Windows and Long Short-Term Memory (LSTM)

Bots in video games has been gaining the interest of industry as well as academia as a problem that has been enabled by the recent advances in deep learning and reinforcement learning. In turn several studies have attempted to establish bot detectors in various video games. In this article, we introduce a bot detection model that can implemented in real-time and provide feedback on whether a player that is being observed is a bot or human. The model uses a limited feature set and amount of time of observation in order to be small and generalize easily to other domains. We trained and tested our model in a series of replays for Starcraft: Brood War and have yielded a higher accuracy than past studies and a fraction of detection time.

AI based Game Bot

AI based Game Bot

Patterns of Cognitive Activity in a Human vs Collaborative Robot Interactive Game

Abstract In order to define different cognitive patterns we analyze sequences of human actions in a game with so-called collaborative robots. Since there are complex win or lose game conditions in this game, in order to win, the player needs to cooperate with one of the bots in the game. Each of the two game bots may cooperate with the player or not during the game, causing the player to change his strategy. In this study, investigations of change of behavioral patterns in different rounds and during each round are performed. To achieve this goal, time series event analysis and analysis of associative rules were performed. The results of this study are a few stable patterns of activity, which are compared with interviews given by participants after the game.

FML-based Dynamic Assessment Agent for Human-Machine Cooperative System on Game of Go

In this paper, we demonstrate the application of Fuzzy Markup Language (FML) to construct an FML-based Dynamic Assessment Agent (FDAA), and we present an FML-based Human–Machine Cooperative System (FHMCS) for the game of Go. The proposed FDAA comprises an intelligent decision-making and learning mechanism, an intelligent game bot, a proximal development agent, and an intelligent agent. The intelligent game bot is based on the open-source code of Facebook’s Darkforest, and it features a representational state transfer application programming interface mechanism. The proximal development agent contains a dynamic assessment mechanism, a GoSocket mechanism, and an FML engine with a fuzzy knowledge base and rule base. The intelligent agent contains a GoSocket engine and a summarization agent that is based on the estimated win rate, real-time simulation number, and matching degree of predicted moves. Additionally, the FML for player performance evaluation and linguistic descriptions for game results commentary are presented. We experimentally verify and validate the performance of the FDAA and variants of the FHMCS by testing five games in 2016 and 60 games of Google’s Master Go, a new version of the AlphaGo program, in January 2017. The experimental results demonstrate that the proposed FDAA can work effectively for Go applications.

Arnold: An Autonomous Agent to Play FPS Games

Advances in deep reinforcement learning have allowed autonomous agents to perform well on Atari games, often outperforming humans, using only raw pixels to make their decisions. However, most of these games take place in 2D environments that are fully observable to the agent. In this paper, we present Arnold, a completely autonomous agent to play First-Person Shooter Games using only screen pixel data and demonstrate its effectiveness on Doom, a classical first-person shooter game. Arnold is trained with deep reinforcement learning using a recent Action-Navigation architecture, which uses separate deep neural networks for exploring the map and fighting enemies. Furthermore, it utilizes a lot of techniques such as augmenting high-level game features, reward shaping and sequential updates for efficient training and effective performance. Arnold outperforms average humans as well as in-built game bots on different variations of the deathmatch. It also obtained the highest kill-to-death ratio in both the tracks of the Visual Doom AI Competition and placed second in terms of the number of frags.

Multimodal game bot detection using user behavioral characteristics.

As the online service industry has continued to grow, illegal activities in the online world have drastically increased and become more diverse. Most illegal activities occur continuously because cyber assets, such as game items and cyber money in online games, can be monetized into real currency. The aim of this study is to detect game bots in a massively multiplayer online role playing game (MMORPG). We observed the behavioral characteristics of game bots and found that they execute repetitive tasks associated with gold farming and real money trading. We propose a game bot detection method based on user behavioral characteristics. The method of this paper was applied to real data provided by a major MMORPG company. Detection accuracy rate increased to 96.06 % on the banned account list.