A real-time autonomic architecture for detection and defeat of open-access chess bots

Abstract

With the rise of online chess, the increasing prevalence of automated chess bots, and recent high-profile cheating controversies, there is growing interest in developing effective methods for detecting bots in chess. Current approaches in this domain largely depend on analyzing player history, detecting anomalies, and conducting engine analysis to identify bot-like behavior after a game has concluded. However, these post-hoc techniques struggle to adapt to real-time detection scenarios, such as those required in dynamic cybersecurity contexts. This paper introduces a novel challenge: detecting bots during an ongoing game, enabling adaptive strategies based on the real-time identification of an opponent’s behavior. It further proposes an autonomic system leveraging self-adaptive properties to address this challenge as well as discussing the application of this bot detection to other domains.