GDC 2018: John McDonald (Valve) - Using Deep Learning to Combat Cheating in CSGO

Channel:max4warn · Length:1:05:32 · Published:2018-03-31 · Views:127839

Watch on YouTube

Summary

A GDC 2018 talk by Valve's John McDonald on VACNet, a deep learning system that analyzes CS:GO gameplay to detect cheaters. It covers how the model is trained on human-reviewed Overwatch cases and how its output feeds human moderation.

Why HN recommends it

HN points to it as the definitive example of server-side, behavioral, non-invasive anti-cheat using machine learning, often as a counterpoint to kernel-level anti-cheat.

The actual presentation is worth listening to if you have the time. — HN, 2020

Security & hacking · Machine learning & deep learning · Game programming & engines

Subtitles (excerpt)

hi so we have a little bit of business before we get started I'm supposed to ask you to pretty please mute your cellphone's so they don't go off and also to make sure to fill out your surveys when you're done or when we're done they're super helpful for GBC to figure out who they should invite back and they're also super useful for me to figure out if you liked the way I presented and you like what I present it so please take a moment when we're done to do that all right that's that's the stuff out of the way let's get started so my name is John McDonald I'm here from valve and today I wanted to come and talk a little bit about how we've been using deep learning to effectively combat cheating in csgo spoiler alert it works pretty well we're pretty happy with it so that's a bunch of stuff we have a whole hour so we're gonna we're gonna cover a lot of ground I'm gonna spend a little bit of time probably a fair warning probably about 15 minutes kind of talking about the state of csgo with respect to cheating other things that we do in this space and then we'll dive into sort of the pitch that I was making to folks around valve in 2016 for why we should maybe give this a try we'll dive into results and then we'll talk a little

On Hacker News

But you can detect serverside (at least probabilistically) if a user is abusing it to their advantage. Some Valve guy gave a great talk about their cheating detection a while back; I found it incredibly impressive: [VIDEO] (can't comment on their effectiveness these days, haven't played CS in a long time) — abuob, 2026-01
See the video above. It’s a condensed recap of Valve’s GDC 2018 presentation on VACnet. The actual presentation is worth listening to if you have the time. [VIDEO] I disagree on the statement that developers, publishers, and/or anticheat companies are too incompetent to implement good solutions. They have not been putting serious effort into the problem or else the state of cheating in video game… — willis936, 2020-01
[VIDEO] Watch this! It's about using ML to catch cheaters. I searched youtube to show you this video; I used the search term "cs go machine learning". The first video was actually this: [LINK] Looks like it's using ML to make better aimbots--lol! — hatsunearu, 2018-10
Valves John McDonald recently gave a talk at Gdc how they use machine learning to combat cheaters in CS:GO. Quite interesting to watch. [VIDEO] — Trellmor, 2018-07
If you wanna something more novel, look at this talk from Valve [0] on how they are integrating Deep Learning into their CS:GO cheater detection system (confusingly called Overwatch). It's not used to ban users, but rather to bring suspicious plays into their existing user-reviewed moderation system. In general, this type of human/AI side-by-side feedback loop seems to be very successful, all the… — ehsankia, 2018-07

Related videos