HackerTube
HomeLongsLikedHistoryWatch laterCategoriesPlaylistsSettings

VACNET Anti-cheat

3kliksphilip1 HN recommender · recommended in 1 month, 2019-2023
YouTube
574K views · 8 years ago · explainer · dated

3kliksphilip summarizes Valve's GDC talk on VACNet, a deep-learning system that flags CS:GO cheaters and feeds the Overwatch review queue. It covers Trust Factor, VAC, and how the data is collected and analyzed.

HN cites it as a source for how Valve uses machine learning on player behavior to detect cheating.

Gaming culture & analysisMachine learning & deep learningSpeedrunning, glitches & game hacking#vacnet#cs:go#valve#deeplearning#overwatch

6 comments from Hacker News

@judge20202023 · in “The Day Windows Died”

That's not what I said - my point is that companies with a relaxed security baseline (ie. not having a dedicated team of people tasked with investigating cheats and improving their anti-cheat system) tend to invite an increased number of cheaters into their games, and I back this up with real events. - These companies will send cease-and-desist letters to cheat makers instead of working to detect their cheats (Joduska.me ceased operations due to a Riot C&D, and Bossland GmbH was actually sued and lost). If these cheats were instead detected and users banned on a continuous basis, no lawsuits would be needed. - CS:GO implemented (as in, almost a decade ago) an "Overwatch" review system to allow players to review potential cheaters and have a consensus on whether or not cheating is likely. Valve is knows to be very relaxed on VAC - and knowing the company culture @ Valve being what it is, these ban waves probably only happen when one of the seniors @ Valve gets killed by a cheater in-game themselves and tasks someone with implementing some detection mechanism into VAC. Only recently (~4 years ago) has valve supposedly started to incorporate more advanced automatic detection and punishment systems[0], but at the time it wasn't doing anything about wallhacks and at auto-headshot cheats tend to be pretty good at adding enough noise to make it look very close to what professionals can do and thus these cases still end up in the overwatch queue (and note that this system probably ha

CitesView on HN
@judge20202021 · in “Epic launches anti-cheat support for Linux, Mac, and Steam Deck”

Worth noting that the VAC games on that list, CS:GO, TF2, and Dota 2, have effectively given up on actually detecting and preventing cheaters and now rely on server-based or community-consensus methods of finding and punishing cheaters (with TF2 being the exception with how little maintenance Valve performs on it). Both CS:GO and Dota 2 have a report+overwatch system where users watch a replay to determine if someone is exhibiting suspicious cheating behavior. The server side of this is VACnet where it uses heuristics like mouse movement or [in Dota] clicking out of regular camera bounds to detect these cheaters and expedite them to the Overwatch queue. You can readily download the biggest script client for Dota 2, and VAC ban waves for using it have been unheard of for years now (you only get an in-game ban when enough other players verify the cheating via Overwatch). ▶ this video link

CitesView on HN
@kllrnohj2021 · in “Valve Steam Deck”

▶ this video Valve is already using machine learning to analyze player mouse movements across all games to look for "inhuman" patterns and send those directly to the community-staffed manual review process called overwatch.

CitesView on HN
@cameronbrown2020 · in “Valve secrets spill over in new Steam documentary app”

If you're interested, Valve uses deep learning model called VACnet to "watch" every player on their servers[0][1]. If any dodgy gameplay is detected, it gets submitted into a moderation queue called Overwatch[2], which is basically delegates the decisions to ban cheaters community. It's really cool how they've gamified this. [0] link [1] ▶ this video [2] link

RecommendsView on HN
@willis9362020 · in “EA is permanently banning Linux players on Battlefield V”

There exist good solutions, but none of these companies have the competence or will to actually solve the problem. It’s security theatre a la malware. “Hey everyone install this rootkit to pretend like we’re preventing cheaters. Don’t worry about the keylogging and screenshot uploading.” What’s most surprising is that the vast majority of gamers aren’t outraged by this at all, despite repeated demonstrations of untrustworthiness by anticheat companies. ▶ this video

CriticalView on HN
@cameronbrown2019 · in “Respawn will deal with Apex Legends cheaters by making them fight each other”

> They also have a neural network setup that constantly scans match logs for cheaters For those wondering what this is referring to, it's a system called VACNet[0] presented at GDC last year. [0] link [1] ▶ this video

CitesView on HN
Robocalypse Now: Using Deep Learning to Combat Cheating in Counter-Strike: Global Offensive1:05:25

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

GDC Festival of Gaming
35K views • 6 years ago
GDC 2018: John McDonald (Valve) - Using Deep Learning to Combat Cheating in CSGO1:05:33

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

max4warn
128K views • 8 years ago
The Day FPS Games Died8:28

The Day FPS Games Died

Basically Homeless
2M views • 5 years ago
Deception, Lies, and CSGO13:48

Deception, Lies, and CSGO

h3h3Productions
9.9M views • 10 years ago
How Valve is Profiting from Steam's Back-Door Casinos36:24

How Valve is Profiting from Steam's Back-Door Casinos

People Make Games
425K views • 4 years ago
Deception, Lies, and Valve24:48

Deception, Lies, and Valve

Coffeezilla
5.7M views • 1 year ago
Overwatch Gameplay Architecture and Netcode1:04:04

Overwatch Gameplay Architecture and Netcode

GDC Festival of Gaming
196K views • 7 years ago
The Dark Side of Counter-Strike 239:19

The Dark Side of Counter-Strike 2

Coffeezilla
5.6M views • 1 year ago
8 Frames in 16ms: Rollback Networking in Mortal Kombat and Injustice 259:38

8 Frames in 16ms: Rollback Networking in Mortal Kombat and Injustice 2

GDC Festival of Gaming
94K views • 7 years ago
Playing a Neural Network's version of GTA V: GAN Theft Auto17:08

Playing a Neural Network's version of GTA V: GAN Theft Auto

sentdex
766K views • 5 years ago
MarI/O - Machine Learning for Video Games5:58

MarI/O - Machine Learning for Video Games

SethBling
11.5M views • 11 years ago
How lucky is too lucky?: The Minecraft Speedrunning Dream Controversy Explained39:47

How lucky is too lucky?: The Minecraft Speedrunning Dream Controversy Explained

Stand-up Maths
8.4M views • 5 years ago
Google's DeepMind AI vs StarCraft 2 World Champion - Game 133:49

Google's DeepMind AI vs StarCraft 2 World Champion - Game 1

ArtosisTV
485K views • 6 years ago
Training an unbeatable AI in Trackmania20:41

Training an unbeatable AI in Trackmania

Yosh
17.7M views • 3 years ago
Deepmind artificial intelligence @ FDOT144:41

Deepmind artificial intelligence @ FDOT14

Elizr
288K views • 12 years ago
First NetHack bot ascension24:44

First NetHack bot ascension

Jan K
20K views • 11 years ago
The Fall of Minecraft's 2b2t23:55

The Fall of Minecraft's 2b2t

FitMC
7.3M views • 5 years ago
Computer program that learns to play classic NES games16:18

Computer program that learns to play classic NES games

suckerpinch
2.2M views • 13 years ago
Console Hacking 2016 (33c3)53:44

Console Hacking 2016 (33c3)

media.ccc.de
166K views • 9 years ago
Free to Play1:15:44

Free to Play

Valve
6.9M views • 12 years ago