[Dailydave] Machine Learning and Dimensions and stuff

[Halvar Flake]

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