Re: Machine Learning for IDS: which dataset?

trantichphuoc@yahoo.com wrote:
> Hi there,
> I am interested in applying machine learning algorithms in detecting network 
> intrusions. I read many papers and realized that the KDD-99 is the most 
> well-known dataset used in the field. However, this dataset is provided by MIT 
> in 1999, and obviously, its pretty old. As we all know, the defensive 
> technologies are fast, and also the hacking techniques. Clearly, the KDD-99 
> dataset would not provide the true representation of a network at the current 
> time. So, could anyone plz tell me which dataset is more updated, specialized 
> for machine learning research in IDS?
> Thanks
> Patrick
>
>
>   
Hi, Patrick.

I am using the KDD-99 dataset in my research work. Though it is the most 
well-known datasets it has several drawbacks that limits what you can do 
with it. As an example, and as you note,  the distribution of normal 
data and attack data does not represents a true real network.

I think that a better dataset is the original used to generate the 
KDD-99 dataset. It can be obtained from www.ll.mit.edu.

Cheers


Juan A. Suárez-Romero

------------------------------------------------------------------------
Test Your IDS

Is your IDS deployed correctly?
Find out quickly and easily by testing it 
with real-world attacks from CORE IMPACT.
Go to http://www.securityfocus.com/sponsor/CoreSecurity_focus-ids_040708 
to learn more.
------------------------------------------------------------------------