Spam Filter
Spam blocker services
Spam Filter Most of the wired world has grown weary of e-mail
invitations to enhance their manhood or buy a certificate allowing them
to marry couples in Idaho, and the folks at Nettwerk Productions in
Vancouver are no different.
But spam has been put in its place now, says Jason Currell, the record
label's system administrator, thanks to technology from another
Vancouver company, ActiveState Corp.
"We were getting complaints constantly," he says.
Nettwerk uses the company's PureMessage mail filtering tool to keep spam
under wraps. While it still reaches the end User--Nettwerk also has
offices in New York, Los Angeles and London, England--questionable
e-mail is marked and sent to a specific folder. This is the default
installation, says Currell, and in the off chance a real e-mail is
deemed spam or a "false positive," users can search their spam folder if
they didn't receive an expected important e-mail.
Before adopting PureMessage, Nettwerk tried a number of in-house
techniques to combat spam, whether it was blocking certain e-mail
servers or subscribing to the RBL--a "real-time blackhole list" which
compiles addresses to be blocked and shares them with Internet users--to
little effect. "It depends on the person, but I would get a hundred or
so a day."
While PureMessage can do more than just defend inboxes against junk
mail--it can filter both inbound and outbound e-mail --spam was the main
reason Nettwerk installed PureMessage, says Currell. He says
PureMessage's approach to dealing with spam made a lot of sense, and
properly addressed the issue of false positives.
"Before these heuristic solutions were out there, there was no solution
really."
It also sits on the mail server, so software doesn't have to be
installed on individual computers.
For Nettwerk, spam is for the most part an annoyance. Currell says it's
not all that worried about being liable for anything potentially
offensive reaching users.
"We have a different sort of crowd here," says Currell. "We're not a law
office. If somebody gets porn in their inbox, they just delete it. I can
see how it would be a problem in other organizations."
According to Chris Kraft, ActiveState's product manager for PureMessage,
the product came into being in 2000 as PureMX when the company realized
it could leverage its expertise in Perl tools to create a platform that
would enable developers to write filters for their e-mail. ActiveState
soon realized it wasn't exactly what customers wanted.
"While the toolset is fine, there's a more immediate problem--that
immediate problem being spam," he says.
Last November the product was rebranded PureMessage to better reflect
what it does.
"While the demand today has largely been driven by virus and now spam,"
says Kraft, "the broader issue is large organizations don't have control
over their e-mail stream.
"There's also concern around what's acceptable use of e-mail," Kraft
adds. "Am I going to allow employees to determine what's appropriate and
what's not in communicating with customers."
Marten Nelson, analyst with San Francisco-based Ferris Research, says
many anti-spam tool vendors started providing general content filtering
solutions and realized customers want anti-spam. Now those vendors are
are simply repositioning the solutions they already have.
Then, there are vendors such as ActiveState, he says, that are investing
in technology that does a good job of filtering spam, he says.
Spam is not the only reason enterprises are adapting mail filtering
technology, but it's definitely what's driving the bulk of sales, says
Nelson.
"When corporations evaluate anti-spam solutions, they realize there's
more beyond resolving spam."
For the latest information about
spam
The Goals of spam
The goal of spam
is to determine the intrinsic grouping in a set of unlabeled data. But
how to decide what constitutes a good spam? It can be shown that
there is no absolute “best” criterion which would be independent of the
final aim of the spam. Consequently, it is the user which must
supply this criterion, in such a way that the result of the spam
will suit their needs.
For instance, we could be interested in finding representatives for
homogeneous groups (data reduction), in finding “natural
clusters” and describe their unknown properties (“natural” data
types), in finding useful and suitable groupings (“useful” data
classes) or in finding unusual data objects (outlier detection).
For the latest information about
The Goals of spam
Who uses spam?
Many different types of organizations use
spam as a vital
part of the work. A sampling of these include:
-
Marketing:
finding groups of customers with similar behavior given a large
database of customer data containing their properties and past
buying records;
-
Biology:
classification of plants and animals given their features;
-
Libraries:
book ordering;
-
Insurance:
identifying groups of motor insurance policy holders with a high
average claim cost; identifying frauds;
-
City-planning:
identifying groups of houses according to their house type,
value and geographical location;
-
Earthquake
studies: spam observed earthquake epicenters to
identify dangerous zones;
-
WWW:
document classification; spam weblog data to discover
groups of similar access patterns.
For the latest information about
Spam Filter