Would it be a good idea to learn viruses as spam?

John Wilcock john at TRADOC.FR
Tue Dec 14 12:53:22 GMT 2004


    [ The following text is in the "ISO-8859-1" character set. ]
    [ Your display is set for the "US-ASCII" character set.  ]
    [ Some characters may be displayed incorrectly. ]

It struck me that most of the Bagle variants we receive here get highish
Bayes scores (90+) whereas most of the Sober.Js still get lowish Bayes
(20 or 30 at most). As new variants of viruses often retain at least
some of the message text from previous variants, it seems to me that it
might be a good idea to teach them to Bayes in the hopes of adding yet
another line of defense to MailScanner's many talents.

What does the combined wisdom of the list reckon on this one? Would it
be a good idea for Julian to implement an option to automatically feed
confirmed viruses to sa-learn --spam?


John.

--
-- Over 2500 webcams from ski resorts around the world - www.snoweye.com
-- Translate your technical documents and web pages    - www.tradoc.fr

------------------------ MailScanner list ------------------------
To unsubscribe, email jiscmail at jiscmail.ac.uk with the words:
'leave mailscanner' in the body of the email.
Before posting, read the MAQ (http://www.mailscanner.biz/maq/) and
the archives (http://www.jiscmail.ac.uk/lists/mailscanner.html).

Support MailScanner development - buy the book off the website!




More information about the MailScanner mailing list