Adventures of a multidimensional freak

This is Juan Julián Merelo Guervós English-language blog. He teaches computer science at the University of Granada, in southern Spain. Come back here to read about politics, technology, with a new twist

Latest comments

  • Customer Service Training en Algorithm::Evolutionary 0.68 is out
  • Customer Service Training en Should Google be taught in Spanish primary schools?
  • Royalflush88 en About conference poster design and defense
  • BIGG BOSS 13 ALL EPISODE en I have to publish something in this blog
  • ReviewPadho en What is informal distributed evolutionary computation?
  • Eugene Williamson en Planes of existence in Thursday Next series
  • techotn_internet_tips_&_tricks en Should Google be taught in Spanish primary schools?
  • Adilkhatri en About conference poster design and defense
  • mo en PPSN'06, Reykjavik
  • mo en PPSN'06, Reykjavik
  • Blogs Out There

    Nelson Minar's Blog
    Jeremy Zawodny's Blog
    Complexes, Carlos Gershenson's blog
    IlliGAL, Genetic Algorithms blog
    Blogging in the wind, Víctor R. Ruiz's blog

    Atalaya, my Spanish language blog
    Geneura@Wordpress, our research group's blog.
    My home page

    Old stories

    Creative Commons License
    This work is licensed under a Creative Commons License.

    Inicio > Historias > Can spam be canned?

    Can spam be canned?

    Short answer: No.
    Longer answer: No way.
    From a theoretical point of view, it's a Turing-decidability problem. It's imposible, in principle, if an email is "unwanted" just by looking at it. You have to understand it, and that takes us a level deeper into machine intelligence that we would be able to code.
    On the other hand, a inmune-system like approach would probably work, at least from the receiving side. As soon as somebody receives an unsolicited email, some kind of antibodies. That was proposed some time ago in an Usenet Posting, and, recently, paper by canadian researchers (PDF) delves deeper into it.
    However, it's not as simple as it looks. Spam messages mutate, so it's difficult to create a unique signature that can be transmitted as an antibody (this is theoretically called a quasispecies); it does not come from a single source, so it cannot identified by vector.
    Are other solutions possible? I'll give short and long answers in the next postings.

    2003-12-10 18:24 | 0 Comment(s) | Filed in

    Referencias (TrackBacks)

    URL de trackback de esta historia


    Dirección IP: (6a787bec0d)
    ¿Cuánto es: diez mil + uno?

    © 2002 - 2008 jmerelo
    Powered by Blogalia