Ethical Hacking

Learn to find vulnerabilities before the bad guys do! Gain real world hands on hacking experience in our state of the art hacking lab. Course designed and taught by expert instructors with years of penetration testing experience. 12 student maximum in every class. Certification attempt included in every package.
Computer Forensics Training at InfoSec Institute

Gain the in-demand skills of a certified computer examiner, learn to recover trace data left behind by fraud, theft, and cybercrime perpetrators. Discover the source of computer crime and abuse at your organization so that it never happens again. All of our class sizes are guaranteed to be 12 students or less to facilitate one-on-one interaction with one of our expert instructors.




Network Security Focus-IDS
[Top] [All Lists]

Re: IDS Datasets

Subject: Re: IDS Datasets
Date: Thu, 31 Aug 2006 10:55:02 +0530
Hi Patrick:
you must be knowing that any learning algorithm is as good as the data presented to it for training. This implies that one should have a very good understanding of data to be used with any learning algo. From your mail, it appears that you have very little knowledge (or not at all) of data used (created by) network devices. Therefore, i advise you to first get yourself familiar with network and related tools (Tcpdump is one of them) and then start working on with your proposal of combining AI and IDS. For that, you would like to look at work done at Columbia Univ, UC davic, Purdue, Gtech etc. Other option is to have someone in your group who is familiar with IDS domain.


regards
-Sanjay
At 07:08 AM 8/28/2006, trantichphuoc@yahoo.com wrote:
Hi there,
I am a newbie in this forum. I am more concerned on Auritficial Intelligence (Machine Learning) techniques rather than the IDS itself. However, I would like to test some machine learning techniques (Neural Networks, ...) in the domain of IDS, i.e. use AI to analyse some available datasets of intrusions.
I found the IDS data published by MIT & DARPA (http://www.ll.mit.edu/IST/ideval/) which is quite wellknown I suppose. I have the following questions:
1. This dataset was published since 1999, which is quite long time ago. However, since then, there is no other "wellknown" dataset of IDS published. I would like to ask if there is some good IDS datasets (ready for AI techniques) but I am not aware of?
2. What is tcp-dump? What I got from the DARPA dataset was a text file with several lines, each line has several attributes separated by commas. How an IDS can understand this text file? I am confusing between the AI-ready datasets (text files that are preprocessed) and the files generated originally from a real IDS.
Thanks
Patrick Tran


------------------------------------------------------------------------
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.
------------------------------------------------------------------------

Sanjay Rawat Security Research Engineer INTOTO Software (India) Private Limited Uma Plaza, Nagarjuna Hills PunjaGutta,Hyderabad 500082 | India Office: + 91 40 23358927/28 Extn 424 Website : www.intoto.com Homepage: http://sanjay-rawat.tripod.com





------------------------------------------------------------------------
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.
------------------------------------------------------------------------


<Prev in Thread] Current Thread [Next in Thread>