Jump to content

Definitely a false positive


Recommended Posts

 

Hi,

We have developed our game with Unreal Engine. I definitely know what Malwarebytes is reporting is false positive.  We are packaging our code with EV code signing and still we are getting this exception from Malwarebytes.  Can you please help us clean this false positive from your end.

https://www.virustotal.com/gui/file/3c8b213077ea4f98e92dc12e80f1645a461095243c8794721be98f8fec85f8e0/detection

PlayImmortal.zip

Link to post
Share on other sites
  • Staff

Hi,

This is detected by our MachineLearning engine, which helps to protect even better against 0day threats. Unfortunately, as this is a heuristic engine, it's possible False Positives happen. Also see here for more explanation:


Thanks for reporting these, as this helps to finetune the engine, so these won't be detected in the future anymore.

This should be fixed by now. Please give it some time (max 10 minutes) in order to have it populate, so detection won't happen anymore.

Additional note, for Virustotal, the fix will be delayed, as we don't have control over this.

Link to post
Share on other sites

We have recently taken a new build and again it started showing error. It was solved, but the same error is coming again. Can you please tell us what could be the reason. is that true that true that every time the binary changes will give the same error again and again.'

 

 

 

 

 

 

image_2021_04_02T11_48_00_460Z.thumb.png.e916a02bb919bd7b36a2f7f63ce18568.png

Link to post
Share on other sites
32 minutes ago, miekiemoes said:

Can you also zip and attach this new build? This so we can also add it to our engine to retrain on it. Having 2 versions of the same always speeds up re-training.

Thanks

I am trying to understand is there no other way to validate this? Means every time we will release a new version we don't want to update it here. Is there any other way to bypass the version related issue?

 

Link to post
Share on other sites
  • Staff

No, it won't be needed everytime. Normally, it's ok with 1 file to add to the machinelearning logic to retrain on it. But if we have more than 1 version of the same, it speeds up training, as it can do better comparison.

But normally, in a 2-3 hours, these and future versions shouldn't be detected anymore anyway.

  • Thanks 1
Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now
  • Recently Browsing   0 members

    No registered users viewing this page.

Back to top
×
×
  • Create New...

Important Information

This site uses cookies - We have placed cookies on your device to help make this website better. You can adjust your cookie settings, otherwise we'll assume you're okay to continue.