hackertube.io

Robocalypse Now: Using Deep Learning to Combat Cheating in Counter-Strike: Global Offensive

GDC Festival of Gaming · talk · Watch on YouTube

What it is

Valve's John McDonald presents at GDC 2018 on how Valve uses deep learning (VACnet) to detect cheaters in Counter-Strike: Global Offensive. He covers training on human-reviewed replays and how model output is confirmed by manual review.

Why Hacker News recommends it

The go-to link in any anti-cheat thread for a concrete, well-delivered account of machine-learning cheat detection in production.

  • 5 people recommended it
  • 6 different months
  • 1 strong recommendations
  • first 2021, last 2025

What HN commenters said

  1. “The presenter delivered the problem and solution approach so well I'd still like to work on something like this some time.”

    Fascinating, well-delivered GDC talk on ML-based cheater detection.

    schmorptron, 2025-06 · Strong recommendation · in “Game Hacking – Valve Anti-Cheat (VAC)”

  2. “Valve do this, here's a good talk”

    Good talk on Valve using deep learning against cheaters.

    crtasm, 2022-02 · Recommendation · in “Thank You, Valve”

  3. “Great talk on it here”

    Great talk on Valve's vacnet with manual review confirmation.

    kllrnohj, 2022-08 · Recommendation · in “The ABI status of ELF hash tables”

  4. “Here's a GDC talk you may find interesting”

    GDC talk on Valve using deep learning against CS:GO cheating.

    arwineap, 2022-11 · Recommendation · in “AI Learns to Play CS:Go via Large-Scale Behavioural Cloning”

  5. “I take this opportunity to share this great talk about Valve's usage of deep learning to fight cheating in CS:GO”

    Great talk about Valve's deep learning use against CS:GO cheating.

    magic123_, 2024-08 · Recommendation · in “Are We Anti-Cheat Yet?”

Excerpts from Hacker News comments, linked to the originals. Summaries and labels were written by a language model from those comments.

Topics: vacnet, cs:go, deep learning, cheat detection, valve, gdc

Also recommended by the same people