Misleading Learners: Co-opting Your Spam Filter

Blaine Nelson, Marco Barreno, Fuching Jack Chi, Anthony D. Joseph, Benjamin I. P. Rubinstein, Udam Saini, Charles Sutton, J. D. Tygar, Kai Xia

Research output: Chapter in Book/Report/Conference proceedingChapter

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.
Original languageEnglish
Title of host publicationMachine Learning in Cyber Trust
Subtitle of host publicationSecurity, Privacy, and Reliability
PublisherSpringer US
Pages17-51
Number of pages35
ISBN (Electronic)978-0-387-88735-7
ISBN (Print)978-0-387-88734-0
DOIs
Publication statusPublished - 2009

Fingerprint

Dive into the research topics of 'Misleading Learners: Co-opting Your Spam Filter'. Together they form a unique fingerprint.

Cite this