Learn, hack!

Hacking and security documentation: slides, papers, video and audio recordings. All in high-quality, daily updated, avoiding security crap documents. Spreading hacking knowledge, for free, enjoy. Follow on .

Keeping the Good Stuff In: Confidential Information Firewalling with the CRM114 Spam Filter & Text Classifier

William Yerazunis
Black Hat USA 2010
Indexed on
Mar 27, 2013
File name
File size
140.3 KB

In this whitepaper we consider the problem of outbound-filtering of emails to prevent accidental leakage of confidential information, We examine how to do this with the GPLed open-source spam filter CRM114 and test the accuracy of this filter against a 10,000+ document corpus of hand-classified emails (both confidential and non-confidential) in Japanese. We look into what moving parts are involved in these filters, and how they can be set up. The results show that a hybrid of multiple CRM114 filters outperforms a human-crafted regular-expression filter by nearly 100x in recall, by detecting > 99.9% of confidential documents, and with a simultaneous false alarm rate of less than 5.3%. As the programmers creating the machine-learning programs don't know how to read or write Japanese, this problem is an almost ideal case of the Searle “Chinese Room” problem.

About us

Secdocs is a project aimed to index high-quality IT security and hacking documents. These are fetched from multiple data sources: events, conferences and generally from interwebs.


Serving 8166 documents and 531.0 GB of hacking knowledge, indexed from 2419 authors from 163 security conferences.


To support this site and keep it alive, you can click on the buttons below. Any help is really appreciated! This service is provided for free, but real money is needed to pay bills.

Flattr this Click here to lend your support to: Keep live SecDocs for an year and make a donation at www.pledgie.com !