Enhancing the efficiency of learning-based spam filters

2007-03-01

Vipul Sharma

Proofpoint, Inc., USA

Steve Lewis

Proofpoint, Inc., USA

Editor: Helen Martin

Abstract

The effectiveness of content-based spam filters is directly related to the quality of the features used in the filter’s classification model. Vipul Sharma and Steve Lewis discuss how retiring features that have become ineffective can improve the filter's performance.

The full article is available to registered users. Click here for free registration or, if you already are a registered user, login to access the full article.

Magazine


	March 2007 PDF Please register to download the PDF Comment Darknet monitoring News News round-up Malware prevalence report January 2007 Analysis Hidan and dangerous Features Peerbot: catch me if you can Real-world testing of email anti-virus solutions Letter Letter to the editor: The strange case of Julie Amero Product review AEC TrustPort Workstation Calendar Anti-malware industry events Spam Bulletin Phishing techniques A phish with a sting in the tail Enhancing the efficiency of learning-based spam filters See also Virus Bulletin archives How to become a subscriber Reprints

Quick Links

Poll

The Japanese government is reported to have commissioned a 'defensive virus'. Is 'defensive' malware ever a good idea?
Leave a comment
View 11 comments

Jobs


	In Virus Bulletin's jobs pages among others: Software Engineer (Broomfield, Colorado, United States) Security Response Engineer (Dublin, Ireland)

Virus Bulletin currently has 224,245 registered users.

Fighting malware and spam

Enhancing the efficiency of learning-based spam filters

Vipul Sharma

Steve Lewis

PDF

Comment

News

Malware prevalence report

Analysis

Features

Letter

Product review

Calendar

Spam Bulletin

See also