SPAM with lots of random words and good words

[pgb at adelard.com]

On 19 Jan 2004 at 15:22, Manvendra Bhangui wrote:

> I have been seeing few messages like the one forwarded below. These
> mails have lot of good words. These get past bogofilter the first time.
> 
> Is it advisable to increase the value of robx to something closer
> to the spam cutoff value so that words that do not occur in wordlist.db
> get a higher score.
> 
> (the mail below is a variation penis enlargement mail) and slipped
> through bogofilter with a spamicity of 0.414806

Suggest you increase the value of mindev (mine is set. to 0.2). With 
a large mindev, unknown words (and words that are roughly neutral) 
are ignored by bogofilter when calculating spamicity.

For example your message (with included spam) was marked as spam by 
my bogofilter, even though it had normal bogofilter headers.

bogofilter would do even better on the pure spam message.

-- 
Peter Bishop 
pgb at adelard.com
pgb at csr.city.ac.uk