EA Is Working On A Way To Detect Saboteurs In Multiplayer Games
Electronic Arts recently published a patent that discusses a technology to detect players that may be sabotaging an online multiplayer video game by conspiring with adversaries (collusion).
The proclaimed collusion detection system could identify saboteurs by pairing suspected players based on their in-game behaviour(s) associated with their own team and the adversary team.
The system will seemingly detect anomalies based on a few characteristics associated with collusion, thereby also determining whether a suspected player is a saboteur or not.
The system may also analyse the social information and past instances of both the players and how they engage with each other and their respective teams within the particular online multiplayer session.
In online multiplayer video games, hacking is one of the most serious violations that a player can commit and one that can cause the player to be banned from playing the video game entirely since it provides an unfair advantage over other players. In recent years, video game companies like Epic Games and Riot Games have constantly strived to prevent such players from exploiting the video game environment through different anti-cheat methods, such as Easy Anti-Cheat and Riot Vanguard. However, while these measures have mostly been auspicious in preventing software and hardware exploitation, they’re still unable to detect players that may intentionally be sabotaging a particular video game by either not playing or playing incorrectly or conspiring with the adversary team to make their own team fail.
While most online multiplayer video games include ways to report such players that may be involved in collusion, Electronic Arts may have found a way to detect saboteurs during the gameplay automatically so as to make it fair for other players. Earlier today, we came across a recently published patent from Electronic Arts under the name of Electronic Arts Inc. titled “DETECTING COLLUSION IN ONLINE GAMES,” which was filed in May 2021 and published only a couple of days ago. “A collusion detection system may detect collusion between entities participating in online gaming,” reads the abstract for the patent.
“The collusion detection system may identify a plurality of entities associated with and opponents within an instance of an online game, determine social data associated with the plurality of entities, determine in-game behavior data associated with the plurality of entities, and determine, for one or more pairings of the plurality of entities, respective pairwise feature sets based at least in part on the social data and the in-game behavior data,” it further reads. Hence, it seems like the collusion detection system could identify saboteurs based on their in-game behaviour(s) associated with their own team and the adversary team.
It further reads, “The collusion detection system may then perform anomaly detection on the respective pairwise feature sets and, in response to the anomaly detection detecting one or more anomalous pairwise feature sets, output one or more suspect pairings of the plurality of entities corresponding to the one or more anomalous pairwise feature sets as suspected colluding pairings.” Hence, the collusion detection system will seemingly detect anomalies based on a few characteristics associated with collusion, thereby also determining whether a suspected player is a saboteur or not.
Earlier this month, we found a recently published patent from Electronic Arts that discussed a similar automated detection system to identify emergent behaviours in-game and adapt to them in near real-time to treat players differently based on their in-game behaviours. Likewise, that patent also aspired to prevent bots and/or malicious players from potentially exploiting video games, so both these patents could be related to each other.
According to the claims of the patent, the collusion detection system will function by determining a pair of players suspected of conspiring with each other from both teams during an online multiplayer session. The pair of players may then be analysed based on a few characteristics, such as their social information, the relation between the players (whether “the relationship is a friend relationship on one of an in-game social platform, a game distribution system social platform or an external platform”), and their past instances within the particular video game.
Furthermore, the collusion detection system may also analyse the ranking of both the players, the time that they’ve spent engaging with each other, the number of items exchanged between them, and the damage they’ve inflicted on each other within the particular online multiplayer session. The patent classifies these instances as anomalies, “outputting one or more suspect pairings of the plurality of entities corresponding to the one or more anomalous pairwise feature sets as suspected colluding pairings.” Additionally, the collusion detection system may also analyse the behaviours of both the suspected players with other players of either team to assess the said anomalies more accurately.
Online multiplayer video games have enabled players from across the world to play and compete together simultaneously. However, competing players that may be involved in collusion can certainly be frustrating to come across. While it’s unclear how Electronic Arts will implement this collusion detection system into its online multiplayer video games, if at all, the company seems to be doing its part of making online multiplayer video games as fair as can be for all players.
What do you think about this? Do tell us your opinions in the comments below!