Hey there,
 

>The implications are though, that even if the adversary adapts, that the ML 
>analytic is forcing the adversary to operate in a smaller space to avoid 
>appearing >anomalous. I consider anything that can shift the balance of cost 
>from the defender to the adversary to be wildly successful. 

No objection that ML-based detections will shift the burden of changing 
something to the attacker. I just predict that long-term success is heavily 
dependent on being able to keep access to the actual classifier out of the 
attackers' hands.

Cheers,
Halvar
 
_______________________________________________
Dailydave mailing list
[email protected]
https://lists.immunityinc.com/mailman/listinfo/dailydave

Reply via email to