Must not be listening to Doug on the nmsusers.org site lists. He plans on using Bayesian filters on network management events to predict causal effects of network issues. Considering that AOL must have boat loads of events, from syslogs, to SNMP traps, to events generated by network management systems, it may help break down the deluge into a manageable amount. Bayesian filters have been around for a while, and are used in bunches of different applications. It's just recently over the last few years that they have been applied to SPAM identification.
Fred Reimer - CCNA Eclipsys Corporation, 200 Ashford Center North, Atlanta, GA 30338 Phone: 404-847-5177 Cell: 770-490-3071 Pager: 888-260-2050 NOTICE; This email contains confidential or proprietary information which may be legally privileged. It is intended only for the named recipient(s). If an addressing or transmission error has misdirected the email, please notify the author by replying to this message. If you are not the named recipient, you are not authorized to use, disclose, distribute, copy, print or rely on this email, and should immediately delete it from your computer. -----Original Message----- From: John Neiberger [mailto:[EMAIL PROTECTED] Sent: Wednesday, September 03, 2003 5:36 PM To: [EMAIL PROTECTED] Subject: RE: OT Gibberish in email [7:74740] Reimer, Fred wrote: > > It is an attempt by the SPAMers to avoid SPAM software that > takes a hash of > the SPAM and blocks SPAM on machines based on these hash > values. There are > some anti-SPAM "solutions" out there that basically relies on > the users to > mark email as SPAM. When they do, the client machines send the > hash of the > SPAM up to the service provider, which shares these hashes with > all other > subscribers. So, if the same exact SPAM is sent to another > user it would > automatically get blocked. These random characters change the > hash value, > and hence this method of blocking SPAM is ineffective. > > Use a Bayesian filter program for your SPAM. I have 3755 > emails in my "Junk > Mail" folder now, and I empty it out last on July 18th. Check > out > www.Junk-Out.com. > > Fred Reimer - CCNA Someone should develop a SPAM filter that looks for certain types of randomness within a message. This would be difficult, but certainly not impossible. You'd have to be pretty creative about it but it ought to be possible to devise an algorithm that could detect that sort of random line--often found in the subject line--and flag it as SPAM. I haven't heard of a Bayesian filter before. I'm going to go find out more about that right now. John **Please support GroupStudy by purchasing from the GroupStudy Store: http://shop.groupstudy.com FAQ, list archives, and subscription info: http://www.groupstudy.com/list/cisco.html Message Posted at: http://www.groupstudy.com/form/read.php?f=7&i=74753&t=74740 -------------------------------------------------- **Please support GroupStudy by purchasing from the GroupStudy Store: http://shop.groupstudy.com FAQ, list archives, and subscription info: http://www.groupstudy.com/list/cisco.html