The default is 5, accepts decimals and can be adjusted to a value lower or higher as determined by the administrator. Used to set the amount of points accumulated, and assigned by SpamAssassin to a message to be considered as spam. If you have a server with CentOS 5 or 6 or Red Hat ™ Enterprise Linux 5 or 6, you can use the following command: Installing the required software Installing via yum. Procmail can be used interchangeably with Sendmail and Postfix. Also allows automatic filtering of e-mail, pre-sorting and other tasks. Procmail is a program that works like MDA ( Mail Delivery Agent) that is used to manage the delivery of local mail system. SpamAssassin is an implementation that uses a scoring system based on a genetic algorithm to identify messages that could be suspected of being unsolicited sent via mass mailings systems, adding headers to the message so that it can be filtered by the email client MUA> ( Mail User Agent). In this article you will see how to configure a service with Spamassassin to identify and discard spam on your mail server. However, once Bayes is working well and reliably, I strongly suggest activating these rescoring lines, which will increase the impact of Bayes on high-confidence determinations.Original article by: : Joel Barrios Dueñas in spanish. # score BAYES_99 9 Notice that I have "#" at the front of these lines, which will intially prevent them from rescoring the BAYES rules.Once you've developed confidence that your ham and spam are being correctly flagged, AWL can be a very powerful tool, but a few mis-categorized emails when first starting up the system can cause emails to be mis-categorized for an extended period of time. use_auto_whitelist 0 I suggest that new users initially turn the AutoWhitelist (AWL) off.I prefer to be more conservative, but YMMV. The default spam auto-learn threshold is 6.0. In that case you may want to use a threshold of 0.0 or 0.001 and hope for the best. Note that if you do not have the ability to create your own rules, and if your host does not have any negative scoring rules, this will effectively turn off Bayes. I prefer to lower this to -0.1, meaning that emails are auto-learned as ham only if they hit some negative-scoring rule somewhere. The default non-spam auto-learn threshold is +0.1, which means that any spam that manages to miss all spam rules can be mistakenly learned as ham. It's on by default, but I like including the bayes_auto_learn parameter in my user_prefs, so if I should need to turn it off, the switch is readily available (set to 0 to turn this off). bayes_auto_learn_threshold_spam 9.0 These three parameters control the Bayes auto-learn function.bayes_auto_learn_threshold_nonspam -0.001.Note: Under version 2.5x and 2.6x, this parameter was named required_hits. If you server is working extremely well, you might consider dropping this required score to 4.5 or 4 (I suggest dropping it 0.1 at a time to avoid suddenly causing a lot of false positives). required_score 5 What score is needed to flag an email as spam (via the X-Spam-Status header)? A brand new user may want to raise this score, perhaps to 6 or 7, until you get confident that your server's parameters do not cause excessive false positives.These configuration parameters should be placed into user-specific $HOME/.spamassassin/user_prefs configuration files (or the SQL equivalents). Setting this to no has side effects of turning of a lot of helpful tests. This enables or disables using dns (disables network tests if set to no). Network Testsĭns_available (yes|no|test) default = test Read the description above for bayes and ask the same questions. This enables using Auto-Whitelist factor. Do you want this?, should you use it for your application?, make sure you know if you need/want this or not before installing. These parameters should be placed into the server-wide local.cf configuration file. This page contains those configuration parameters that almost everyone will want to consider using as they install or begin using SpamAssasssin. SpamAssassin allows for very flexible configuration.
0 Comments
Leave a Reply. |