Dark Reading is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them.Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

Partner Perspectives  Connecting marketers to our tech communities.
SPONSORED BY
3/14/2017
11:00 AM
Pieter Arntz
Pieter Arntz
Partner Perspectives
Connect Directly
Twitter
RSS
50%
50%

7 Things You Need to Know about Bayesian Spam Filtering

Knowing how spam filters work can clarify how some messages get through, and how your own emails can avoid being caught.

Bayesian spam filtering is based on Bayes rule, a statistical theorem that gives you the probability of an event. Bayesian filtering is used to give you the probability that a certain email is spam.

1. The Name
It’s named after the statistician the Rev. Thomas Bayes, who provided an equation that allows new information to update the outcome of a probability calculation. The rule is also called the Bayes-Price rule after the mathematician Richard Price, who recognized the importance of the theorem, made some corrections to Bayes’ work, and put the rule to use.

2. Spam
When dealing with spam the theorem is used to calculate a probability about whether a certain message is spam. The probability is based on words in the title and message, derived from messages that were identified as spam and messages that were identified as not being spam (sometimes called ham).

3. False positives
The objective of the learning ability is to reduce the number of false positives. As annoying as it might be to receive a spam message, it is worse to not receive a message from a customer just because he used a word that triggered the filter.

4. Scoring
Other methods often use simple scoring filters. If a message contains specific words a few points are added to that messages’ score and when it exceeds a  certain score, the message is regarded as spam. Not only is this a very arbitrary method, it’s also a given that it will result in spammers changing their wording. Take for example “Viagra” which is a word that will surely give you a high score. As soon as spammers found that out they switched to variations like “V!agra” and so on. This is a  cat and mouse game that will keep you busy creating new rules.

5. Learning
If the filtering is allowed for individual input the precision can be enhanced on a per-user base. Different users may attract specific forms of spam based on their online activities. In other words,  what is spam to one person is a “must-read” newsletter to the next. Every time the user confirms or denies that a message is spam, the filtering process can calculate a more refined probability for the next occasion.

6. Poisoning
A downside of Bayesian filtering, in cases of more-or-less targeted spam, is that spammers will start using words or whole pieces of text that will lower the score. During prolonged use, these words might get associated with spam, which is called poisoning.

7. Bypasses
A few methods to bypass “bad word” filtering.

  • The use of images to replace words that are known to raise the score

  • Deliberate misspelling, as mentioned earlier.
  • Using homograph letters, which are characters from other character-sets that look similar to letters in the messages’ character set. For example, the Omicron from the Greek looks exactly the same as an “O," but has a different character encoding.

Bayesian filtering is a method of spam-filtering that has a learning ability, although limited. Knowing how spam filters work will clarify how some messages get through, and how you can make your own mails less prone to get caught in a spam filter.

Links to more information:

Was a Microsoft MVP in consumer security for 12 years running. Can speak four languages. Smells of rich mahogany and leather-bound books. View Full Bio
Comment  | 
Print  | 
More Insights
Comments
Newest First  |  Oldest First  |  Threaded View
COVID-19: Latest Security News & Commentary
Dark Reading Staff 7/9/2020
Introducing 'Secure Access Service Edge'
Rik Turner, Principal Analyst, Infrastructure Solutions, Omdia,  7/3/2020
Russian Cyber Gang 'Cosmic Lynx' Focuses on Email Fraud
Kelly Sheridan, Staff Editor, Dark Reading,  7/7/2020
Register for Dark Reading Newsletters
White Papers
Video
Cartoon
Current Issue
Special Report: Computing's New Normal, a Dark Reading Perspective
This special report examines how IT security organizations have adapted to the "new normal" of computing and what the long-term effects will be. Read it and get a unique set of perspectives on issues ranging from new threats & vulnerabilities as a result of remote working to how enterprise security strategy will be affected long term.
Flash Poll
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2020-15001
PUBLISHED: 2020-07-09
An information leak was discovered on Yubico YubiKey 5 NFC devices 5.0.0 to 5.2.6 and 5.3.0 to 5.3.1. The OTP application allows a user to set optional access codes on OTP slots. This access code is intended to prevent unauthorized changes to OTP configurations. The access code is not checked when u...
CVE-2020-15092
PUBLISHED: 2020-07-09
In TimelineJS before version 3.7.0, some user data renders as HTML. An attacker could implement an XSS exploit with maliciously crafted content in a number of data fields. This risk is present whether the source data for the timeline is stored on Google Sheets or in a JSON configuration file. Most T...
CVE-2020-15093
PUBLISHED: 2020-07-09
The tough library (Rust/crates.io) prior to version 0.7.1 does not properly verify the threshold of cryptographic signatures. It allows an attacker to duplicate a valid signature in order to circumvent TUF requiring a minimum threshold of unique signatures before the metadata is considered valid. A ...
CVE-2020-15299
PUBLISHED: 2020-07-09
A reflected Cross-Site Scripting (XSS) Vulnerability in the KingComposer plugin through 2.9.4 for WordPress allows remote attackers to trick a victim into submitting an install_online_preset AJAX request containing base64-encoded JavaScript (in the kc-online-preset-data POST parameter) that is execu...
CVE-2020-4173
PUBLISHED: 2020-07-09
IBM Guardium Activity Insights 10.6 and 11.0 does not set the secure attribute on authorization tokens or session cookies. Attackers may be able to get the cookie values by sending a http:// link to a user or by planting this link in a site the user goes to. The cookie will be sent to the insecure l...