Team for Research in
Ubiquitous Secure Technology

Citation
B. Nelson, M. Barreno, F. Chi, A. Joseph, B. Rubinstein, U. Saini, C. Sutton, D. Tygar, K. Xia. "Misleading learners: Co-opting your spam filter". Springer, pp. 17-51, 2009.

Abstract
Using statistical machine learning for making security decisions introduces new vulnerabilities in large scale systems. We show how an adversary can exploit statistical machine learning, as used in the SpamBayes spam filter, to render it useless—even if the adversary’s access is limited to only 1% of the spam training messages. We demonstrate three new attacks that successfully make the filter unusable, prevent victims from receiving specific email messages, and cause spam emails to arrive in the victim’s inbox.

Electronic downloads

• misleading.learners.pdf · application/pdf · 608 kbytes

• HTML

  B. Nelson, M. Barreno, F. Chi, A. Joseph, B. Rubinstein, U.
  Saini, C. Sutton, D. Tygar, K. Xia. <a
  href="http://www.truststc.org/pubs/723.html"
  >Misleading learners: Co-opting your spam
  filter</a>, <i> Springer</i>, pp. 17-51, 
  2009.

• Plain text

  B. Nelson, M. Barreno, F. Chi, A. Joseph, B. Rubinstein, U.
  Saini, C. Sutton, D. Tygar, K. Xia. "Misleading
  learners: Co-opting your spam filter". <i>
  Springer</i>, pp. 17-51,  2009.

• BibTeX

  @article{NelsonBarrenoChiJosephRubinsteinSainiSuttonTygarXia09_MisleadingLearnersCooptingYourSpamFilter,
      author = {B. Nelson and M. Barreno and F. Chi and A. Joseph
                and B. Rubinstein and U. Saini and C. Sutton and
                D. Tygar and K. Xia},
      title = {Misleading learners: Co-opting your spam filter},
      journal = { Springer},
      pages = {17-51},
      year = {2009},
      abstract = {Using statistical machine learning for making
                security decisions introduces new vulnerabilities
                in large scale systems. We show how an adversary
                can exploit statistical machine learning, as used
                in the SpamBayes spam filter, to render it
                useless—even if the adversary’s access is
                limited to only 1% of the spam training messages.
                We demonstrate three new attacks that successfully
                make the filter unusable, prevent victims from
                receiving specific email messages, and cause spam
                emails to arrive in the victim’s inbox.},
      URL = {http://www.truststc.org/pubs/723.html}
  }
  

Posted by Jessica Gamble on 7 Apr 2010.
For additional information, see the Publications FAQ or contact webmaster at www truststc org.