<?xml version="1.0" encoding="utf-8"?>
<rss version="2.0"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
     xmlns:admin="http://webns.net/mvcb/"
     xmlns:content="http://purl.org/rss/1.0/modules/content/"
     xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
	<channel>
	  <title>Ask MetaFilter questions tagged with imagespam</title>
      <link>http://ask.metafilter.com/tags/imagespam</link>
      <description>Questions tagged with 'imagespam' at Ask MetaFilter.</description>
	  <pubDate>Wed, 11 Oct 2006 12:13:56 -0800</pubDate> <lastBuildDate>Wed, 11 Oct 2006 12:13:56 -0800</lastBuildDate>

      <language>en-us</language>
	  <docs>http://blogs.law.harvard.edu/tech/rss</docs>
	  <ttl>60</ttl>	  
	<item>
	<title>Image spam woes</title>
	<link>http://ask.metafilter.com/48385/Image%2Dspam%2Dwoes</link>	
	<description>The amount of image spam I&apos;m getting has snowballed in the past few months.  What can I do? By image spam, I mean where spammers send their text content as a GIF image and then put a paragraph of unrelated text, like the Gettysburg Address, in plain text, to fool Bayesian filters.&lt;br&gt;
&lt;br&gt;
I use PocoMail and K9.  K9&apos;s Bayesian filtering does not work, no matter how many hundreds of messages I train it on (and I&apos;m having concerns this will start snagging legitimate messages).  I posted on the K9 forum and got no real response, so maybe it&apos;s time to switch programs.&lt;br&gt;
&lt;br&gt;
Ideas for flagging image spam?  I don&apos;t expect spam filters to OCR an image (though it doesn&apos;t seem farfetched to detect the sharp angular patterns of text).  However I think spam protection has focused too heavily on Bayesian filtering of text, and is not asking questions like &quot;what is this image doing here?&quot;&lt;br&gt;
&lt;br&gt;
And no, I can&apos;t go to GMail because the domain name I have to use is that of my small business.  Bucketloads of spam get into GMail anyway, from what I&apos;ve seen.</description>
	<guid isPermaLink="false">tag:ask.metafilter.com,2006:site.48385</guid>
	<pubDate>Wed, 11 Oct 2006 12:13:56 -0800</pubDate>
	<category>image</category>
	<category>imagespam</category>
	<category>spam</category>
	<dc:creator>rolypolyman</dc:creator>
	</item>
	<item>
	<title>Filtering Gmail image spam</title>
	<link>http://ask.metafilter.com/45558/Filtering%2DGmail%2Dimage%2Dspam</link>	
	<description>Argh! &lt;a href=&quot;http://labnol.blogspot.com/2006/05/how-to-bypass-gmail-spam-filters.html&quot;&gt;Gmail image spam!&lt;/a&gt; I&apos;m getting 20 of these a day. Since Google has failed to filter these messages, is there a workaround I can use? Also, would simply deleting these messages rather than marking them as spam reduce the possibility of false positives?</description>
	<guid isPermaLink="false">tag:ask.metafilter.com,2006:site.45558</guid>
	<pubDate>Wed, 30 Aug 2006 10:16:14 -0800</pubDate>
	<category>filter</category>
	<category>gmail</category>
	<category>google</category>
	<category>imagespam</category>
	<category>spam</category>
	<dc:creator>Saucy Intruder</dc:creator>
	</item>
	
	</channel>
</rss>

