Deep Neural Network Model for Detection of Cheating in Competitive Chess

CSEF · 2023 Mathematical Sciences Second Award

Overview

Modern computer chess programs capable of easily beating any human player are causing a crisis in the world of competitive chess. These programs are simple to use and can be run on personal computers and even smartphones, allowing users to immediately find the best move from any position in a chess game. This has led to a significant increase in cheating in both online and over-the-board chess matches, resulting in player bans, multi-million-dollar lawsuits, and even criminal charges, but it is hard to prove that a player used assistance from a computer to cheat unless the player is caught in the act. Currently the best mathematical evidence for cheating comes from using statistics to determine the chance that a player could perform above their skill level for many games in a row, but this is not hard proof because 1) a player may play extremely well from time to time without cheating, and 2) a smart cheater might deliberately lose a game occasionally to fool the statistics. For this project I built and trained a neural network to find patterns that cheaters use. I analyzed hundreds of real grandmaster games and used the Stockfish chess engine to generate a large number of games used to train a neural network built with the TensorFlow python library. Moves were chosen to match the statistics of real players and known cheaters. My trained network can detect cheating within a single game with high accuracy.

Source coverage

This record comes from a published award list, not a complete project archive. Its abstract comes from CSEF's public project showcase as archived by the Internet Archive before judging (https://web.archive.org/web/20230401224130/https://ca-csef.zfairs.com/showcase/ShowcaseInfo?f=838e60b7-ea75-46e8-865c-fde4864244b3); the version presented may differ.

Awards (1)

Competition history

  • CSEF 2023 Mathematical Sciences · Entry J1418

Resources

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

Source: California Science & Engineering Fair public projects

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. An account also raises your daily allowance for “Has this been done?”, and lets you create a key for the MCP server with a much higher limit than anonymous use. Browsing stays public.

Continue with Google