Cordially Advice you to register to Dark Reading(Webinar)

There will be a conference on 6/04/2016 Insights for a More Secure Enterprise against DDoS attacks and other Security Threats 

Tuesday, April 5, 2016 | 10AM PST / 1PM EST

You can register and listen to the discussion and even ask questions

Speakers: 

Evan Uhl  CISSP CRISC, Senior Manager Neustar Security Operations

Christina Richmond Program Director, Security Services IDC

Cordially Advice you to register to Dark Reading(Webinar)

There will be a conference on 6/04/2016 Insights for a More Secure Enterprise against DDoS attacks and other Security Threats 

Tuesday, April 5, 2016 | 10AM PST / 1PM EST

You can register and listen to the discussion and even ask questions

Speakers: 

Evan Uhl  CISSP CRISC, Senior Manager Neustar Security Operations

Christina Richmond Program Director, Security Services IDC

Dear Monowar,

I never heard about "ensemble-base approach" however by quickly looking the definition in the wikipedia ("Ensemble methods use multiple learning algorithms to obtain better predictive performance than could be obtained from any of the constituent learning algorithms.[1][2][3] Unlike a statistical ensemble in statistical mechanics, which is usually infinite, a machine learning ensemble refers only to a concrete finite set of alternative models, but typically allows for much more flexible structure to exist among those alternatives.") I dare to say YES! Actually there are already some papers on DDoS attacks that uses ensemble-based approach. See bellow:

- http://www.sciencedirect.com/science/article/pii/S0140366411000600

-http://www.sciencedirect.com/science/article/pii/S0140366412003222

-http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5466662

So, my message for you is: read those papers, find a sweet spot that you can do something new, and prove that you are right =D