Join Jose Mora on Amplify
The Web's Social News Network.

Curate, connect & build relationships you'll learn from.

Jose Mora | My Amplog

The truth is out there, distributed in the web
« Amplog Home   Posts tagged: spam
  • Name: Jose Mora
  • Twitter:
  • Web: jmora.tumblr.com
  • Bio: I'm a PhD student in artificial intelligence interested in computers, research and specially and more specifically on artificial intelligence.
14224

Jose Mora is following

HansWobbe
ericleebow

Use bots for spam, to avoid it, I mean

A new technique to detect spam consists on using a bot generating that spam to reverse engineer the template of the messages that it is sending. It is debatable how useful that may be, considering the time that may take and the little time needed to send vast amounts of spam.

What would happen if this technique was used upon spam reception, knowing there may b... read more

Amplify’d from www.newscientist.com

To beat spam, turn its own weapons against it

Researchers have now come up with a system that deciphers the templates a botnet is using to create spam. These templates are then used to teach spam filters what to look for.

Each message is generated from a template that specifies the message content and how it should be varied. The team reasoned that analysing such messages could reveal the template that created them
the team installed a previously captured software bot onto a machine. After analysing 1000 emails generated by this compromised machine - less than 10 minutes’ work for most bots - the researchers were able to reverse-engineer the template
The new system did not produce a single false positive when tested against more than a million genuine messages
botnets have grown so large that even a 1-minute delay in cracking the template would be “long enough for a very substantial spam campaignRead more at www.newscientist.com