Exploiting Machine Learning to Subvert Your Spam Filter

  title={Exploiting Machine Learning to Subvert Your Spam Filter},
  author={Blaine Nelson and Marco Barreno and Fuching Jack Chi and Anthony D. Joseph and Benjamin I. P. Rubinstein and Udam Saini and Charles A. Sutton and J. Doug Tygar and Kai Xia},
Using statistical machine learning for making security decisions introduces new vulnerabilities in large scale systems. This paper shows 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 training messages. We further demonstrate a new class of focused attacks that successfully prevent victims from receiving specific email messages. Finally, we introduce two new types… CONTINUE READING
Highly Influential
This paper has highly influenced 13 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 178 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 103 extracted citations

178 Citations

Citations per Year
Semantic Scholar estimates that this publication has 178 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 23 references

A statistical approach to the spam problem

  • Gary Robinson
  • Linux Journal,
  • 2003
Highly Influential
4 Excerpts

Chung and Aloysius K . Mok . Advanced allergy attacks : Does a corpus really help ?

  • P Simon
  • Recent Advances in Intrusion Detection ( RAID…
  • 2006

Chung and Aloysius K . Mok . Allergy attack against automatic signature generation

  • P. Simon
  • Proceedings of the ACM Symposium on InformAtion…
  • 2006

A USENET corpus

  • Cyrus Shaoul, Chris Westbury
  • http: //www.psych.ualberta.ca/ ̃westburylab…
  • 2005
1 Excerpt

Similar Papers

Loading similar papers…