Introduction

---

AntispamSniper for The Bat! provides a comprehensive anti-spam and anti-phishing protection for your mailbox. The combination of several methods for automatic email classification shows impressive filtering quality with minimum error rate. The plug-in also has a built-in option allowing deleting spam on the server by headers.

What methods are used?

• First of all, it is a statistical trainable classification algorithm with unique characteristics. It learns your private correspondence, extracts the distinguishing features from messages of different classes and uses that information for effective analysis of the other incoming messages. The algorithm improves its classification quality continuously with each new learned message.
  
  
• The messages from whitelisted senders are not filtered by other methods and recognized as non-spam at once. The whitelist is optionally updated on learning automatically.
  
  
• The filtering rules are recognizing spam and normal messages by specific combinations of symbols in body and headers of the message. The rules are optional, because the trained algorithm and a whitelist are very effective. But the accurately assembled lists of rules may improve the classification quality in cases when the algorithm is unable to select a certain class for a message with high probability.
  
  
• Exceptions are the empirical conditions for filtering. For example, large messages are probably non-spam. The presence of certain types of attached files also can be a good sign for recognizing message as non-spam.
  
  
• Anti-phishing filter blocks the messages with spoofed links and thereby protects you from the phishing attacks.
  
  
• DNSBL services are used for blocking spam by IP address of the sender.
  
  
• A list of black words is used for deleting spam by keywords in subject.
  
  
• The plug-in optionally learns the outgoing messages as non-spam.
  
  
• The plug-in can delete spam right on the server, using a list of account settings. The accounts for filtering can be added manually or automatically for non-secure connections.
  

The classifier starts working right after installation and recognizes the spam with rather good quality. For improving the filtering quality you should configure plug-in according to instructions from Getting started guide.