Comment by Xss3
2 days ago
Anticheat devs could REALLY benefit by having some data scientists involved.
Any player responding to ingame events (enemy appeared) with sub 80ms reaction times consistently should be an automatic ban.
Is it ever? No.
Given good enough data a good team of data scientists would be able to make a great set of rules using statistical analysis that effectively ban anyone playing at a level beyond human.
In the chess of fps that is cs, even a pro will make the wrong read based on their teams limited info of the game state. A random wallhacker making perfect reads with limited info over several matches IS flaggable...if you can capture and process the data and compare it to (mostly) legitimate player data.
> Any player responding to ingame events (enemy appeared) with sub 80ms reaction times consistently should be an automatic ban.
It's really much more nuanced than that. Counter-Strike 2 has already implemented this type of feature, and it immediately got some clear false positives. There are many situations where high level players play in a predictive, rather than reactive, manner. Pre-firing is a common strategy that will always look indistinguishable from an inhuman reaction time. So is tap-firing at an angle that you anticipate a an opponent may peek you from.
You mustve missed the part where i spoke of consistency?
Ive played at the pro level. Nobody prefires with perfect robotic consistency.
I dont care if it takes 50 matches of data for the statistical model to call it inhuman.
Valve has enough data that they could easily make the threshold for a ban something like '10x more consistent at pre-firing than any pro has ever been' with a high confidence borne over many engagements in many matches.
> Nobody prefires with perfect robotic consistency.
Then all you need to do to fool this anticheat is to add some randomness to the cheat.
2 replies →
There's well analyzed video of a pro player streaming who got temporarily banned for something like this. It might not even have been pre-fire, but post-fire at a different enemy retreating at the same position
https://youtu.be/SFyVRdRcilQ
Valve need to tweak the model so that it requires a higher confidence level before a ban, and to reduce false positives in their data capture methods. This is a mistake but doesnt kill the idea.
We used to track various timings in some of our games to detect cheating. Cheaters find out and change their cheat engines to perform within plausible human reactions. Which is a benefit - now the cheating isn't obvious to everyone, but it still happens. I don't know if you could sprinkle data scientist dust on the problem and come up with a viable cross-game solution though.
Thats a win. Preventing cheaters gaining superhuman advantage significantly reduces their impact.
Tomorrow the cheats will be back with human looking reaction speeds and inhuman decision making that is indistinguishable from expert players.
Good! Thats actually one of the goals. Reduce the advantage cheaters can gain to within human bounds. They can cheat to feel like a good player, but not a god.
"Any player responding to ingame events (enemy appeared) with sub 80ms reaction times consistently should be an automatic ban."
Can you define what "reacting" means exactly in a shooter, that you can spot it in game data reliable to apply automatic bans?
>Can you define what "reacting" means exactly in a shooter
A human can't really, which is why you need to bring in ML. Feed it enough game states of legit players vs known cheaters, and it will be able to find patterns.
There is no need for ML. Games arent the real world.
A suitable game engine would have knowledge of when a shadow, player, grenade, noise, or other reactable event occurs for a given client.
Especially if games arent processed in real time but processed later based on a likelihood of cheating drawn from other stats.
And what happens to that pattern, when the cheat engine adjusts? What happens to the enraged players that got wrongly banned for cheating?
3 replies →
Anisotropic mouse movement?
Or perhaps the 0ms-80ms distribution of mouse movement matches the >80ms mouse movement distribution within some bounds. I'm thinking KL divergence between the two.
The Kolmogorov-Smirnov Test for two-dimensional data?
There's a lot of interesting possible approaches that can be tuned for arbitrary sensitivity and specificity.
Throwing in ML jargon and going straight to modelling before understanding the problem reduces your credibility as a data scientist in front of engineers and stakeholders.
As always, one of the most difficult parts is getting good features and data. In this case one difficulty is measuring and defining the reaction time to begin with.
In Counter Strike you rely on footsteps to guess if someone is around the corner and start shooting when they come close. For far away targets, lots of people camp at specifc spots and often shoot without directly sighting someone if they anticipate someone crossing - the hit rate may be low but it's a low cost thing to do. Then you have people not hiding too well and showing a toe. Or someone pinpointing the position of an enemy based on information from another player. So the question is, what is the starting point for you to measure the reaction?
Now let's say you successfully measured the reaction time and applied a threshold of 80ms. Bot runners will adapt and sandbag their reaction time, or introduce motions to make it harder to measure mouse movements, and the value of your model now is less than the electricity needed to run it.
So with your proposal to solve the reaction time problem with KL divergence. Congratulations, you just solved a trivial statistics problem to create very little business value.
10 replies →
Like another commentor mentioned, I think that only works for a specific cheat(engine) - as long as they don't adjust (and randomize more for example). If it could be solved with some statistics, I think it would have been done already. I ain't a statistician though, but if you feel confident, I think there is quite some money in it, if you find a real world solution.
2 replies →