SA-MP Forums

Go Back   SA-MP Forums > Other > Everything and Nothing

Reply
 
Thread Tools Display Modes
Old 17/12/2018, 11:03 AM   #1
Yashas
Gangsta
 
Join Date: Jun 2012
Location: India
Posts: 878
Reputation: 313
Default AI based AntiAimbot [with DEMO]

RELEASED: https://forum.sa-mp.com/showthread.php?t=662075

I'm working on an server-side aimbot detector which already has working code (you can plug it in your server and test).

Repository Link
The documentation is present in the README.md in the subdirectories and example filterscripts.

DEMO

Detailed demo video (18th December): https://www.*******.com/watch?v=BUl2NU3YRxw

I'm still experimenting with it and not sure if a model which generalizes for all players in all conditions can be built but it's still worth a try. I need lots of data that needs to be collected. If you are interested in contributing, please join AntiAimbot Discord Server

Last edited by Yashas; 28/12/2018 at 04:01 PM.
Yashas is offline   Reply With Quote
Old 17/12/2018, 04:22 PM   #2
Onfroi
High-roller
 
Onfroi's Avatar
 
Join Date: Jan 2012
Location: Dallas, Texas
Posts: 1,716
Reputation: 222
Default Re: AI based AntiAimbot [with DEMO]

That's pretty interesting, VACnet for samp
__________________
Onfroi is offline   Reply With Quote
Old 17/12/2018, 05:32 PM   #3
DeitY
Huge Clucker
 
DeitY's Avatar
 
Join Date: Aug 2012
Location: Serbia
Posts: 321
Reputation: 14
Default Re: AI based AntiAimbot [with DEMO]

Quote:
Originally Posted by Yashas View Post
I'm working on an server-side aimbot detector which already has working code (you can plug it in your server and test).

Repository Link
The documentation is present in the README.md in the subdirectories and example filterscripts.

DEMO

I'm still experimenting with it and not sure if a model which generalizes for all players in all conditions can be built but it's still worth a try. I need lots of data that needs to be collected. If you are interested in contributing, please join AntiAimbot Discord Server
How reliable is this? I have high count playerbase, i can let them collect insane amount of data if it helps in any way.

While i do not lay so much hope in this, at-least someone is doing what Kalcor needed to fix 10 years ago.
__________________
Kasno je za oprostaj ; )

DeitY is offline   Reply With Quote
Old 17/12/2018, 06:05 PM   #4
Yashas
Gangsta
 
Join Date: Jun 2012
Location: India
Posts: 878
Reputation: 313
Default Re: AI based AntiAimbot [with DEMO]

Quote:
Originally Posted by DeitY View Post
How reliable is this?
The current models are very unreliable.

What you are seeing in the video:
- me handpicking the video where it performed best
- model trained to detect ONLY me using aimbot
- model trained to detect in a local server (almost ideal network conditions)
- trained to work only with M4
- trained with exactly one kind of aimbot
- 98% accuracy

The moment I had put the same model online:
- ~90% (IIRC) accuracy

It would not work when multiple players are involved by design (the training data that was used). For example, the SVM tries to find the maximum margin hyperplane, i.e. it would place the hyperplane such that it neatly separates my skillset from the aimbot skill set but in reality, there would be players who would have a skill set somewhere in between. Hence, it is expected to fail.

Hence, I am trying to collect data from many players. I expect to see a normally distributed variables for non-aimbots and a distribution skewed significantly to the higher skill set for aimbots. When combined, it would hopefully give a nice distribution with a bump at the higher skillset range. But I'm not really sure if it'll turn out this way. There could also be players who are as skilled as imperfect aimbots.

The AI machinery works on a transformed dataset. The raw data is analyzed and transformed into samples which are statistics about the last 8-20 shots. The collected raw data is filtered where almost all of the shots are rejected. There are heavy restrictions on the allowed samples:
- must use M4
- ping less than X
- victim must be moving
- gap between shots must be less than Y ms
- hit series must have a ratio more than 0.5+
- more here and here

Since the problem was complex, the idea of adding restrictions was to reduce the number of variables and ease the learning process which appears to have worked. I also switched to a simple deep neural network and it performed as good as the SVM. Currently there detections are based on two detectors running parallel: SVM and DNN. Tomorrow, I'll be adding a RF detector (which actually did pretty good).

It's also using very poorly engineered set of features for training (transformed vectors contain just 16 numbers) but for unexpected reasons, it's working so I haven't bothered putting more efforts on feature engineering until I see a significant drop in accuracy (which I will eventually).

Quote:
Originally Posted by DeitY View Post
I have server of 900 + players count, i can let them collect insane amount of data if it helps in any way.

While i do not lay so much hope in this, at least someone is doing what Kalcor needed to fix 10 years ago.
Initially, I thought of collecting data from live servers and use them as negative samples. It would be a decent approximation that most of the players do not use aimbots. But then collecting a nearly equal number of aimbot data still becomes a problem. A small number of aimbot samples cannot be used because the data collected from the live servers already contain noise and data from many players who are using aimbots. The quality of the data would also be low.

Currently, the strategy that is being followed is: collect a minimal amount of data and train the detector to classify aimbot users whenever possible and not always. Hence, the aimbot samples which are being collected is OBVIOUS aimbot samples only. For example, a sample that is taken with a player shooting another player who is running in a straight line using an aimbot is not a great one since even a player since there would be similar samples without using aimbots.

Live Server Statistics
Code:
SVM Results:
positive test set statistics: 
average: 0.895024, stddev: 0.202378
min: 0.16941, max: 0.998552
skewness: -2.59443, excess kurtosis: 6.30058
negative test set statistics: 
average: 0.0636774, stddev: 0.10247
min: 0.000767444, max: 0.385762
skewness: 2.28472, excess kurtosis: 4.20898
true positives: 39, false positives: 0
true negatives: 38, false negatives: 3
number of samples classified corretly: 77
number of samples classified incorrectly: 3
accuracy: 0.9625

RF Results:
positive test set statistics: 
average: 0.855925, stddev: 0.234815
min: 0.068, max: 1.045
skewness: -1.74412, excess kurtosis: 2.32794
negative test set statistics: 
average: 0.108018, stddev: 0.148063
min: -0.0975, max: 0.5665
skewness: 1.58524, excess kurtosis: 2.14748
true positives: 37, false positives: 1
true negatives: 37, false negatives: 5
number of samples classified corretly: 74
number of samples classified incorrectly: 6
accuracy: 0.925

DNN Results:
true positives: 39, false positives: 2
true negatives: 36, false negatives: 3
number of samples classified corretly: 75
number of samples classified incorrectly: 5
accuracy: 0.9375
The accuracy looks pretty high because it was trained on a small dataset (500 samples with one kind of aimbot with data from 6 people). It'll mostly fall as more aimbots and players' data is added. Another option might be to have different detectors for each weapon, aimbot, etc. but this will also become computationally expensive.
Yashas is offline   Reply With Quote
Old 17/12/2018, 05:54 PM   #5
Kar
High-roller
 
Kar's Avatar
 
Join Date: May 2010
Location: Black Asylum
Posts: 3,172
Reputation: 511
Default Re: AI based AntiAimbot [with DEMO]

Tests are looking good. Keep it up.
Kar is offline   Reply With Quote
Old 18/12/2018, 01:31 PM   #6
Yashas
Gangsta
 
Join Date: Jun 2012
Location: India
Posts: 878
Reputation: 313
Default Re: AI based AntiAimbot [with DEMO]

Detailed demo video: https://www.*******.com/watch?v=BUl2NU3YRxw
Yashas is offline   Reply With Quote
Old 18/12/2018, 02:39 PM   #7
Variable™
Gangsta
 
Join Date: Jul 2015
Location: Somewhere...
Posts: 781
Reputation: 164
Default Re: AI based AntiAimbot [with DEMO]

Interesting. I hopped in.
__________________
MW4 Community

Variable™ is offline   Reply With Quote
Old 21/12/2018, 12:00 PM   #8
xPrabhat
Little Clucker
 
Join Date: Dec 2018
Posts: 3
Reputation: 0
Default Re: AI based AntiAimbot [with DEMO]

Still its kinda hard to detect aimbot if the player is using desert eagle,sniper...sawn off shotgun.. sometimes a human eye could be best for these cases however you can't have admins online 24/7 but a system can work 24/7.
xPrabhat is offline   Reply With Quote
Old 21/12/2018, 01:08 PM   #9
Yashas
Gangsta
 
Join Date: Jun 2012
Location: India
Posts: 878
Reputation: 313
Default Re: AI based AntiAimbot [with DEMO]

The detectors were trained using M4 data. It was yesterday tested with AK47 and MP5 and it worked great. Many kinds of aimbots were also tested and it detected all of them given enough time and there was exactly one false positive throughout the day. These statistics may not hold for a live server.

I'll make an experimental release today or tomorrow for people to test.

There is a public test server where any two people can test the detectors.

HostName: [0.3.7] AntiAimbot Data Collection Server
Address: 85.204.97.138:7777

HostName: [0.3DL] AntiAimbot Data Collection Server
Address: 85.204.97.138:8888

Last edited by Yashas; 21/12/2018 at 06:18 PM.
Yashas is offline   Reply With Quote
Old 21/12/2018, 03:57 PM   #10
K0P
Gangsta
 
K0P's Avatar
 
Join Date: Nov 2015
Location: *.*.*.*
Posts: 601
Reputation: 84
Default Re: AI based AntiAimbot [with DEMO]

Evolutionary algorithm implemented in SAMP. UNIQUE
__________________
OptionComment
GitHubAll of the scripts made by me can be found here.
Contact InfoClick here if you want to contact me.

Not a CSGO beggar!
K0P is offline   Reply With Quote
Reply

Thread Tools
Display Modes

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off


Similar Threads
Thread Thread Starter Forum Replies Last Post
FIFA 15 Demo fiki574 Everything and Nothing 13 12/09/2014 04:59 PM
[FilterScript] San Andreas Singleplayer cheats[cmd based and text based] Rayan_black Filterscripts 26 09/06/2014 04:35 AM
Converting a mysql based to .ini based Johnny_Robins Server Support 6 04/07/2012 07:06 PM
A roleplay server based on a military based war? CobraAziz General 21 05/05/2012 07:15 AM
F.E.A.R 2 Demo Lewwy Everything and Nothing 18 25/01/2009 06:52 PM


All times are GMT. The time now is 12:59 AM.


Powered by vBulletin® Version 3.8.6
Copyright ©2000 - 2019, Jelsoft Enterprises Ltd.