News Other

Microsoft files patent to detect cheating in games with machine learning

Ai to detect cheating.jpg

Microsoft filed a patent at the United States Patent and Trade Office for machine learning to detect cheating in video games and report on player achievements and progress. Machine learning is where an AI program collects data, analyzes it, and learn from it by recognizing patterns for example. It can also make decisions based on what it has learned from the data collected. In a way, it has similar properties to that of data mining.

In the not too distant future, Artificial Intelligence will detect cheating and report on player performance.

"Online gaming has become more and more popular as wide area network access across the world has become more available. Online game players may interact within both social and competitive environments. Over time, players may gain status among a gaming community by meeting defined goals, such as by earning achievements, in various games," explains Microsoft. "Examples are disclosed that relate to detecting cheating at a game platform level using machine learning techniques.

One example provides a computing system comprising a logic subsystem and a data-holding subsystem. The data-holding subsystem comprises instructions executable by the logic subsystem to receive notifications related to user progress in a game provided by the game to the online game platform, apply a classifying function to classify the user progress in the game as normal or outlying based upon the notifications, if the progress is classified as outlying then taking an action in response to the outlying classification, and if the progress is not classified as outlying then not taking the action."

So, the AI learns from the data it collects about you from the moment you've logged into Xbox Live. It looks at your performance say in first-person shooters and how fast and accurate you react in combat, or your reaction time when playing a real-time strategy game. Then it compares it to your performance in similar games and eventually, it draws logical conclusions about your skill level. If you suddenly perform overly well, then it detects an anomaly and you get kicked for cheating. A sophisticated program like this will, of course, also have the usual tick boxes for cheating in place, for example, aimbot and wallhack detection.

In the submission, Microsoft highlights an important fact, with today's cheat-detection systems it is increasingly difficult to catch cheaters in third-party games.

"However, such mechanisms may only detect cheating occurring within the game itself. As such, a platform that hosts third party games may not be able to detect cheating that occurs in third party games, even where achievements in third party games are managed at the platform level.

Thus, examples are disclosed that relate to detecting cheating in online games based upon interactions between the games and a game platform that hosts the games. As explained in more detail below, the disclosed examples use one or more classification functions trained by machine learning techniques to track interactions between a game and a game platform, such as notifications of achievements, game scores reported to the platform, and/or a player rank achieved on the platform based upon game activities."

Just imagine the computing power required for such a thing to be able to process millions of player data and implementing its conclusions. Machine learning has been around for decades, and where it was first just a program that served as pattern recognition software, in more recent times it developed into something with the ability to learn.

It reminds me of the Singularity Theory that believes there will one day be artificial superintelligence because technology will feed on technology until it surpasses human intelligence. And we all know what happens next.

But I digress, machine learning is already implemented in much of our online lives. How else is Netflix able to give you that list of recommendations? Investors use it for market analysis, the entertainment industry uses it to recommend products to customers. I have a friend who studied Applied Mathematics and today he works for a company that provides voice biometrics solutions for homeland security and corporate clients. Years ago he told me that they use machine learning to catch terrorists.

So why not use machine learning to catch cheaters? The patent has yet to be approved or rejected.

I remember the days when I was an admin for Team Fortress 2. The hours we spent watching recordings because someone accused someone of cheating. It was a nightmare and a massive waste of time. I hope AI cheat detection is part of the future of gaming.

What's your take on this? Something to welcome, or something that will be impossible to work effectively?

News via

Han: Twitter / GameZone: Twitter Facebook | Instagram | YouTube

"detecting cheating at a game platform level using machine learning techniques"

Other news from around the NET:

Recent Comments

Community on Disqus

Latest Reviews

Forza Horizon 4 Review

Forza Horizon 4 Review


With a gorgeous open world, epic car roster and a new seasonal system, this year's Forza is the best...

V-Rally 4 Review

V-Rally 4 Review


V-Rally 4 delivers some great off-road racing that all rally fans will enjoy.

comments powered by Disqus