spamassassin-users mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Steven W. Orr" <ste...@syslang.net>
Subject RE: Fundamental question about spam image processing.
Date Mon, 02 Apr 2007 16:26:02 GMT
On Monday, Apr 2nd 2007 at 12:18 -0400, quoth Rob McEwen (PowerView Systems):

=>> It turns out that the basis for their analysis is to look at 
=>> the size of 
=>> the image as well as the number of colors. 99.99% of all spam 
=>> images have 
=>> less than 16 colors. Once they found an image with 22 colors. 
=>> This sounds 
=>> like a dirt cheap way to get a huge boost in spam 
=>> recognition. They may 
=>> have other tricks they do, but I just wanted to report what I learned.
=>
=>Sounds great... but this begs the question... what strategies do they 
=>use to ensure that someone's GIF logo in a legit e-mail doesn't cause 
=>that legit e-mail to get blocked as spam? In other words, for this to be 
=>an effective strategy, wouldn't it ALSO need to be true that these stats 
=>are NOT typically the case for images in legit e-mail?

My understanding is that the size of the image is the discriminator. 
Logo's tend to be smaller than image spam or short and wide and a header 
across the top. Also, logos tend to be huge in bytecount and are 
frequentlt displayed as shrunk. The size and the number of colors seems to 
be key.

-- 
Time flies like the wind. Fruit flies like a banana. Stranger things have  .0.
happened but none stranger than this. Does your driver's license say Organ ..0
Donor?Black holes are where God divided by zero. Listen to me! We are all- 000
individuals! What if this weren't a hypothetical question?
steveo at syslang.net

Mime
View raw message