Dailydave mailing list archives
Re: Machine Learning and Dimensions and stuff
From: "Halvar Flake" <HalVar () gmx de>
Date: Sat, 22 Nov 2014 11:34:56 +0100
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 Dailydave () lists immunityinc com https://lists.immunityinc.com/mailman/listinfo/dailydave
Current thread:
- Machine Learning and Dimensions and stuff Dave Aitel (Nov 20)
- Re: Machine Learning and Dimensions and stuff Halvar Flake (Nov 20)
- Re: Machine Learning and Dimensions and stuff William Kupersanin (Nov 21)
- Re: Machine Learning and Dimensions and stuff shadown [at] gmail (Nov 22)
- Re: Machine Learning and Dimensions and stuff William Kupersanin (Nov 22)
- Re: Machine Learning and Dimensions and stuff Halvar Flake (Nov 22)
- Re: Machine Learning and Dimensions and stuff Parity (Nov 22)
- Re: Machine Learning and Dimensions and stuff William Kupersanin (Nov 21)
- Re: Machine Learning and Dimensions and stuff Halvar Flake (Nov 20)
- <Possible follow-ups>
- Re: Machine Learning and Dimensions and stuff Sven Krasser (Nov 24)
- Re: Machine Learning and Dimensions and stuff Oleg Kolesnikov (Nov 27)