Twitter Spamdetector Service

At the International Secure Systems Lab, we have developed a couple of services like Anubis, Wepawet, or FIRE. Lately, we have worked on a mechanism to detect spammers on Twitter, a popular microblogging service. We have developed several heuristics to detect spamming profiles, and have already reported thousands of these profiles to Twitter, who then shut down these profiles. Now we have created a profile to which users can flag spammers on Twitter: the flagged accounts are added to our database, allowing us to detect profiles from campaigns we did not observe before.

The profile is @spamdetector, and the messages it accepts are of the format
"@spamdetector @spamaccount"

Whenever you see a suspicious account, you can simply send us a notification and our system will check if this account is likely a spammer or not. This helps us to improve our heuristics, and we can help Twitter to shut down suspicious profiles, leading to a better service.

This work was carried out by Gianluca Stringhini, a PhD student at University of California, Santa Barbara, working as research assistant at the Computer Security lab. And you can find my tweets at @thorstenholz.


    No Trackbacks


Display comments as (Linear | Threaded)

  1. Matrix says:

    Due to the growth of Twitter (we recently started to Twit too) this is a wise step.
    Worldwide Spam uses most e-mail traffic, so every effort to resolve this issue is very positive..

Add Comment

E-Mail addresses will not be displayed and will only be used for E-Mail notifications

To prevent automated Bots from commentspamming, please enter the string you see in the image below in the appropriate input box. Your comment will only be submitted if the strings match. Please ensure that your browser supports and accepts cookies, or your comment cannot be verified correctly.