Comment by lukan
2 days ago
"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?
Yeah, that's why you need a data scientist or two to figure that stuff out. Its a solvable problem, but you're not going to get solutions instantly for free in the reply section of HN.
1 reply →
If anyone is wrongly banned the system is too sensitive. Let it capture data for a month before banning someone. Ensure the confidence is crazy high.
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.
Appreciate the feedback, you're right - armchair speculation is different than actual data science. Without actual data to examine, we're left with the latter and that can still be a fun exercise even if it doesn't solve any business problem. We're here to chitchat and converse after all.
1 reply →
More like congrats, you just made every cheater far less effective by forcing them to play nearer to human limits.
You arent eliminating cheaters, that's impossible, you are limiting their impact.
7 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.
Even randomisation would cause their aim to be statistically different to a normal players aim over time.
To be sure. There's at most 6 frames of data per event to work with at 60fps. It's an interesting problem and well suited to statistics.