Robocalypse Now: Using Deep Learning to Combat Cheating in Counter-Strike: Global Offensive
5 人推荐 · 跨 6 个月 · 2021–2025
中文导读
Valve 工程师 John McDonald 在 GDC 2018 上的干货分享，系统揭秘了 CS:GO 如何利用深度学习反作弊系统（VACnet）打击作弊者，包括利用人工审查录像训练模型，以及模型预测与人工复核闭环的工业落地架构。
为什么 HN 推它
任何反作弊技术讨论帖里的必看标杆，罕见由一线大厂毫无保留分享的工业级机器学习反作弊实战经验。
「主讲人把痛点和解决思路讲得太精彩了，甚至让我产生了一种想投身搞这个方向的冲动。」HN 网友原话：The presenter delivered the problem and solution approach so well I'd still like to work on something like this some time.
英文原摘要（HackerTube / Claude 整理）
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.
The go-to link in any anti-cheat thread for a concrete, well-delivered account of machine-learning cheat detection in production.
HN 上的提及
There's a really good talk that someone from valve gave about 3 years ago[0].
John McDonald did a talk at GDC 2018 about how Valve was starting to integrate deep learning into their server-side cheat detection.
Valve do this, here's a good talk
As far as I'm aware Valve does use ML (called VACnet) to detect cheaters.
Great talk on it here