spamoracle - a spam classification tool

spamoracle [-config conf] [-f database] mark [ mailbox ... ]

spamoracle [-config conf] [-f database] add [-v] -spam spambox ... -good goodbox ...

spamoracle [-config conf] [-f database] test [-min prob] [-max prob] [ mailbox ... ]

spamoracle [-config conf] [-f database] stat [ mailbox ... ]

spamoracle [-config conf] [-f database] list regexp ...

spamoracle [-config conf] [-f database] backup > backupfile

spamoracle [-config conf] [-f database] restore < backupfile

spamoracle [-config conf] [-f database] words [ mailbox ... ]

SpamOracle is a tool to help detect and filter away "spam" (unsolicited commercial e-mail). It proceeds by statistical analysis of the words that appear in the e-mail, comparing the frequencies of words with those found in a user-provided corpus of known spam and known legitimate e-mail. The classification algorithm is based on Bayes' formula, and is described in Paul Graham's paper, A plan for spam, http://www.paulgraham.com/spam.html.

This program is designed to work in conjunction with procmail(1). The result of the analysis is output as an additional message header X-Spam: followed by yes, no or unknown, plus additional details. A procmail rule can then test this X-Spam: header and deliver the e-mail to the appropriate mailbox.

In addition, SpamOracle also analyses MIME attachments, extracting relevant information such as MIME type, character encoding and attached file name, and summarizing them in an additional X-Attachments: header. This allows procmail to easily reject e-mails containing suspicious attachments, e.g. Windows executables which often indicate a virus.

To use SpamOracle, your mail must be delivered to a Unix machine on which you have a shell account. This machine must have procmail(1) (see http://www.procmail.org/) installed. Your ~/.forward file must be set up to run all incoming e-mail through procmail(1). If your mail server supports the POP or IMAP protocols, you can also use fetchmail(1) to fetch your mail from the server and have it delivered to your local machine.

To provide the corpus of messages from which SpamOracle "learns", an archive of about 1000 of your e-mails is needed. The archive must be manually or semi-automatically split into known spams and known good messages. Mis-classified messages in the corpus (e.g. spams mistakenly stored among the good messages) will decrease the efficiency of the classification. The archive must be in Unix mailbox format, or in "one message per file" format (a la MH). Other formats, such as Emacs' Babyl, are not supported.

The notion of "word" used by SpamOracle is slanted towards Western European languages, i.e. the ISO Latin-1 and Latin-9 character sets. Preliminary support for JIS-encoded Japanese can be selected at compile-time. SpamOracle will not work well if you receive many legitimate e-mails written in other character sets, such as Chinese or Korean sets.

To build the database of word frequencies from the corpus, do:

rm ~/.spamoracle.db
spamoracle add -v -good goodmails -spam spammails

spamoracle add -good goodmails1 ... goodmailsN
spamoracle add -spam spammails1 ... spammailsP

To check that the database was built correctly, and familiarize yourself with the statistical analysis performed by SpamOracle, invoke the "test" mode on the mailboxes that you just used for building the corpus:

spamoracle test goodmails | more
spamoracle test spammails | more

 From: bbo <midhack@ureach.com>
 Subject: Check This Out
 Score: 1.00 -- 15
 Details: refid:98 $$$$:98 surfing:98 asp:95 click:93 cable:92
   instantly:90 https:88 internet:87 www:86 U4:85 isn't:14 month:81
   com:75 surf:75 
Attachments: cset="GB2312" type="application/octet-stream"
   name="Guangwen4.zip" 
 File: inbox/314

The Score: line summarizes the result of the analysis. The first number (between 0.0 and 1.0) is the probability that the message is actually spam --- or, equivalently, the degree of similarity of the message with the spam messages in the corpus. The second number (an integer between 0 and 15) is the number of "interesting" words found in the message. "Interesting" words are those that occur at least 5 times in the corpus. In the example, we have 15 interesting words (the maximum) and a score of 1.00, indicating a spam with high certainty.

The Details: line provides an explanation of the score. It lists the 15 most interesting words found in the message, that is, the 15 interesting words whose probability of denoting a spam is farthest away from the neutral 0.5. Each word is given with its individual score, written as a percentage (between 01 and 99) rather than as a probability so as to save space. Here, we see a number of very "spammish" words such as $$$$ or click, with probability 0.98 and 0.93 respectively, and a few "innocent" words such as isn't (probability 0.14). The U4 word with probability 0.85 is actually a pseudo-word representing a 4-letter word all in uppercase -- something spammers are fond of.

The Attachments: line summarizes some information about MIME attachments for this message. Here, we have one attachment of type application/octect-stream, file name Guangwen4.zip, and character set GB2312 (an encoding for Chinese).

The File: line shows the file that is being tested.

Normally, when running spamoracle test goodmails, most messages should come out with low score (0.2 or less), and when running spamoracle test spammails, most messages should come out with a high score (0.8 or more). If not, your corpus isn't very good, or not well classified into spam and non-spam. To quickly see the outliers, you can reduce the interval of scores for which message summaries are displayed, as follows:

spamoracle test -min 0.2 goodmails | more
       # Shows only good mails with score >= 0.2
spamoracle test -max 0.8 spammails | more
       # Shows only spam mails with score <= 0.8

spamoracle test mymailbox | less

Once the database is built, you're ready to run incoming e-mails through SpamOracle. The command spamoracle mark reads one e-mail from standard input, and copies it to standard output, with two headers inserted: X-Spam: and X-Attachments:. The X-Spam: header has one the following formats:

" X-Spam: yes; score; details

or

" X-Spam: no; score; details

or

" X-Spam: unknown; score; details

The score and details are as described for spamoracle test.

The yes/no/unknown tag synthesizes the results of the analysis: yes means that the score is >= 0.8 and at least 5 interesting words were found; no means that the score is <= 0.2 and at least 5 interesting words were found; unknown is returned otherwise. The unknown case generally occurs for very short messages, where not enough interesting words were found.

The X-Attachments: header contains the same information as the Attachments: output of spamoracle test, that is, a summary of the message attachments.

To process automatically your incoming e-mail through SpamOracle and act upon the results of the analysis, just insert the following "recipes" in the file ~/.procmailrc:

:0fw
| /usr/local/bin/spamoracle mark

:0 * ^X-Spam: yes; spambox

What these cryptic commands mean is:

- Run every mail through the spamoracle mark command. (If spamoracle wasn't installed in /usr/local/bin, adjust the path as necessary.) This adds two headers to the message: X-Spam: and X-Attachments:, describing the results of the spam analysis and the attachment analysis.

- If we have an X-Spam: yes header, deliver the message to the file spambox rather than to your regular mailbox. Presumably, you'll read spambox once in a while, but less often than your regular mailbox. Daring users can put /dev/null instead of spambox to just throw away the message, but please don't do that until you've used SpamOracle for a while and are happy with the results. SpamOracle's false positive rate (i.e. legitimate mails classified as spam) is low (0.1%) but not null. So, better save the presumed spams somewhere, and scan them quickly from time to time.

If you'd like to enjoy a bit of attachment-based filtering, here are some procmail rules for that:

:0
* ^X-Attachments:.*name=".*\.(pif|scr|exe|bat|com)"
spambox

:0 * ^X-Attachments:.*type="audio/(x-wav|x-midi) spambox

:0 * ^(Content-type:.*|X-Attachments:.*cset="|^Subject:.*=\?)(ks_c|gb2312|iso-2|euc-|big5|windows-1251) spambox

The first rule treats as spam every mail that has a Windows executable as attachment. These mails are typically sent by viruses. The second rule does the same with attachments of type x-wav or x-midi. I never normally receive music by e-mail, however some popular e-mail viruses seem fond of these attachment types. The third rule treats as spam every mail that uses character encodings corresponding to Korean, Chinese, Japanese, and Cyrillic.

At any time, you can add more known spams or known legitimate messages to the database by using the spamoracle add command.

For instance, if you find a spam message that was not classified as such, run it through spamoracle add -spam, so that SpamOracle can learn from its mistake. (Without additional arguments, this command will read a single message from standard input and record it as spam.) Under mutt(1) for instance, just highlight the spam message and type

|spamoracle add -spam

Another option is to collect more known spams or more known good messages into mailbox files, and once in a while do spamoracle add -good new_good_mails or spamoracle add -spam new_spam_mails.

For your edification and entertainment, the contents of the database can be queried by regular expressions. The spamoracle list regexp command lists all words in the database that match regexp (an Emacs-style regular expression), along with their number of occurrences in spam mail and in good mail. For instance:

spamoracle list '.*' # show all words -- big list!
spamoracle list 'sex.*'
spamoracle list 'linux.*'

The database used by SpamOracle is stored in a compact, binary format that is not humanly readable. Moreover, this format is subject to change in later versions of SpamOracle. To facilitate backups and upgrades, the database contents can also be manipulated in a portable, text format.

The spamoracle backup command dumps the contents of the database to standard output, in a textual, portable format.

The spamoracle restore command reads such a dump from standard input and rebuilds the database with this data.

The recommended procedure for upgrading to a newer version of SpamOracle is:

# Before the upgrade:
spamoracle backup > backupfile
# Upgrade SpamOracle
# Restore the database
spamoracle restore < backupfile

Many of the parameters that govern message classification can be configured via a configuration file. By default, the configuration is read from the file .spamoracle.conf in the user's home directory. A different configuration file can be specified on the command line using the -config option: spamoracle -config myconfigfile ...

The list of configurable parameters and the format of the configuration file are described in spamoracle.conf(5).

All parameters have reasonable defaults, but you can try to improve the quality of classification further by tweaking them. To determine the impact of your changes, use either the test or stat commands to spamoracle. The spamoracle stat command prints a one-line summary of how many spam, non-spam, and unknown messages were found in the mailboxes given as arguments.

SpamOracle's notion of "word" is any run of 3 to 12 of the following characters: letters, single quotes, and dashes (-). If support for non-English european languages was compiled in, word characters also include the relevant accented letters for the languages in question. All words are mapped to lowercase, and accented letters are mapped to the corresponding non-accented letters.

A run of 3 to 12 of the following characters also constitutes a word: digits, dots, commas, and dollar, Euro and percent signs.

In addition, a run of three or more uppercase letters generates a pseudo-word Un where n is the length of the run. Similarly, a run of three or more non-ASCII characters (code >= 128) generates a pseudo-word Wn where n is the length of the run.

For instance, the following text:

SUMMER in English is written "ete" in French

U5 summer english written ete french W3

U5 summer english written french W3

To see the words that are extracted from a message, issue the spamoracle words command. It reads either a single message from standard input, or all messages from the mailbox files given as arguments, decomposes the messages into words and prints the words.

The database file can be compressed with gzip(1) to save disk space, at the expense of slower spamoracle operations. If the database file specified with the -f option has the extension .gz, spamoracle will automatically uncompress it on start-up, and re-compress it after updates.

If your mail is stored in MH format, you may run into "command line too long" errors while trying to process a lot of small files with the spamoracle add command, e.g. when doing

spamoracle add -good archives/*/* -spam spam/*

Instead, do something like:

find archives -type f -print | xargs spamoracle add -good

find spam -type f -print | xargs spamoracle add -spam

Xavier Leroy <Xavier.Leroy@inria.fr>

spamoracle.conf(5); procmail(1); fetchmail(1)

http://cristal.inria.fr/~xleroy/software/ (SpamOracle distribution site)

http://www.paulgraham.com/spam.html (Paul Graham's seminal paper)