FAQs for Spam Filter Express

Will Spam Filter Express work with AVG 7.0 or other Anti-virus software?

Yes. There are not any compatibility problems for Spam Filter Express with AVG 7.0, Spywareblaster, Adaware SE or any other ant-virus software products. We have tested it and Spam Filter Express works well with them.

Will Spam Filter Express coexist with my current message rules??

Yes. Unlike most spam filter software products usually do, Spam Filter Express will never add special words such as '[spam]' or '***spam***' to the subject line of your original email message and add Message Rules to Outlook or Outlook Express. This is the reason why Spam Filter Express coexist well with your current message rules. Any incoming emails to the Inbox folder will be checked by Spam Filter Express and the spam emails will be moved to the ‘Spam’ folder. For any incoming emails redirected by the message rules to any other folders, you may use the ‘Spam Filter Express->Filter Current Folder’ toolbar menu to filter out spam emails.

Does Spam Filter Express require any server software or extensions?

Not at all. Spam Filter Expressis a plug-in for your Outlook or Outlook Express client, and runs solely on your PC.

What if my company has spam-filtering software already installed on our server?

Spam Filter Express will run in parallel with your company’s server software. Like anti-virus products, you need protection on the server as well as your desktop.

What happens to my junk emails?

Sapm Filter Express moves all suspected junk emails to the Spam folder--a sub-folder of your Inbox.

How do I know Sapm Filter Express does not eliminate good emails?

You can open the Spam folder and look through it to assure yourself that it does not contain any good email messages.

What happens if I accidentally mark a good email as Spam?

Simply go to your Spam folder, select the email you accidentally marked as Spam, and press the "Recover from Spam" button. Spam Filter Express will undo its previous learning about that email and move the email back to your Inbox.

Does Spam Filter Express ever delete my email?

Never. Spam Filter Express only moves email to folders.

Where does the spam go?

The spam messages are placed in a spam folder located in the root of your local folders. 

How do I delete spam from the spam folder?

-- Click the Spam Filter Express toolbar. There will be a pop-up menu

-- Click the Empty “Spam” Folder sub-menu  .

-- All spam emails will be moved into the Deleted Items folder. 

How can I see what Spam Filter Express is blocking?

Open your Spam Folder to view all spam messages Spam Filter Express moved to it. If you find a legitimate message in the Spam Folder, select it and then click the Recover As Good button. The message is moved to your Inbox and will not be blocked in the future.

What Are False-Positives?

Anti-spam systems often block the delivery of legitimate email. When this happens, the blocked message is referred to as a "false-positive" result.Spam Filter Express's technology was developed specifically to eliminate the "false-positive" problem. Its near zero false-positive rate is unmatched by any competitors, making it the most accurate and reliable anti-spam system available.

Can I run a clean-up on my Inbox?

Although Spam Filter Express filters all new incoming emails, you can clean up a folder that contains spam emails before Spam Filter was installed. To clean up a folder with old spam emails, select the folder and then, on the Spam Filter Express toolbar button menu, click Filter Current Folder. All messages are scanned and known spam emails are automatically moved to the Spam Folder.

How can I backup the trained database?

To backup the databases, all you need to do is make a copy of the directory that Spam Filter Express keeps its data in. If you need to, you can drop the files back in to recover from a corrupted database, or for any other reason.

This directory is located in the directory which you have installed Spam Filter Express (usually at C:\Program Files\Spam Filter Express\db). The two most vital files found in the DB directory and are called mcwords.db and namelist.db. These 2 files hold all Spam Filter Express spam and good emails knowledge.

If your database becomes corrupted, you will be able to recover without losing all your data. You may also copy these files if you need to install Spam Filter Express on another computer and keep all the trained information.

Will Spam Filter Express work with Eudora or any other email clients?

No, Spam Bully currently only works with Outlook and Outlook Express. More email clients will be supported in our future versions.

What if I have a technical question about Spam Filter Express?

Please send all questions and product feedback to support@spam-filter-express.com. We will answer your questions as quickly as possible.

What is Bayesian Filter and how it works?

Bayesian filters are more or less based on the Bayes rule, a theory of conditional probability that estimates the likelihood of an event (hypothesis) given the certainty of another event (evidence). Basically, the rule says that the likelihood of an event occurring in the future can be inferred from the number of times it occurred in the past.

The Bayesian filter works on studying the e-mail and also the spam that you have received in the past. These create two collections a good collection, consisting of all the real e-mails you received and the bad collection which consists of all the spam you have received in the past. It counts the number of times each word in the good collection occurs in the good collection and creates a table. It does the same for the bad collection with the end result being two tables, one for the good collection and one for the bad collection.

The filter uses these tables when constructing probabilities for future e-mail it encounters being spam. In other words, Bayesian filter determines whether a new e-mail you receive is spam or real e-mail based on your past e-mail and your past spam. The following picture shows the Bayesian filtering procedures.

Original source from: http://www.pcmag.com/article2/0,1759,1567368,00.asp

The first step for Bayesian filtering is to create a tailor-made Bayesian word database. Before mail can be filtered using this method, the user needs to generate a database with words and tokens (such as the $ sign, IP addresses and domains, and so on), collected from a sample of spam emails and legitimate emails (referred to as ‘ham’). A probability value is then assigned to each word or token: the probability is based on calculations that take into account how often that word occurs in spam as opposed to legitimate email (ham). This is done by analyzing the users' outbound mail and by analyzing known spam: All the words and tokens in both pools of mail are analyzed to generate the probability that a particular word points to the mail being spam. This word probability is calculated as follows: If the word "Vigor" occurs in 300 of 3,000 spam mails and in 3 out of 300 legitimate emails, for example, then its spam probability would be 0.999 (that is, [300/3000] divided by [3/300 + 300/3000]).

The second step is to create the ham database (tailored to your company). It is important to note that the analysis of ham mail is performed on the company's mail, and is therefore tailored to that particular company. For example, a financial institution might use the word "mortgage" many times over and would get a lot of false positives if using a general anti-spam rule set. On the other hand, the Bayesian filter, if tailored to your company through an initial training period, takes note of the company's valid outbound mail (and recognizes "mortgage" as being frequently used in legitimate messages), and therefore has a much better spam detection rate and a far lower false positive rate.

The third step is to create the spam database. Besides ham mail, the Bayesian filter also relies on a spam data file. This spam data file must include a large sample of known spam and must be constantly updated with the latest spam by the anti-spam software. This will ensure that the Bayesian filter is aware of the latest spam tricks, resulting in a high spam detection rate (note: this is achieved once the required initial two-week learning period is over).

The last step of Bayesian filtering is to classify the incoming email by calculating the spam probability of the new message. Once the ham and spam databases have been created, the word probabilities can be calculated and the filter is ready for use. When a new mail arrives, the filter does the following:

• Break incoming e-mail into its constituent words
• Calculate the probability that each of the words is spammy.
• Combine the probability of these words using Bayesian combination techniques to derive an overall probability that the E-Mail is spam.

If the probability is greater than a threshold, say 0.9, then the message is classified as spam.

Why Bayesian filters are better?

It is hard to create a set of rules that would be accepted by everyone to define spam, but each individual may know what he or she considers to be spam when he or she sees it. That means that the best way to categorize spam is for each person to categorize it by example.

Bayesian spam filters are based on real world examples of spam, which are used to classify future e-mail. There are at least four advantages using Bayesian filtering technology to identify spams.

1)Bayesian filters are advantageous because they take the whole context of a message into consideration. Unlike other filtering techniques that look for spam-identifying words in subject lines and headers, a Bayesian filter uses the entire context of an e-mail when it looks for words or character strings that will identify the e-mail as spam. For example, Bayesian filters examine the words in a body of an e-mail, its header information and metadata, word pairs and phrases and even HTML code that can identify. In other words, Bayesian filtering is a much more intelligent approach because it examines all aspects of a message, as opposed to keyword checking that classifies a mail as spam on the basis of a single word.

2) A Bayesian filter is constantly self-adapting. Bayesian filters are adaptable in that the filter can train itself to identify new patterns of spam. It generally act faster to block new types of spam e-mails. This is because rule and list based spam blockers react to spam, they do not anticipate it. Each set of rules or sender names to be blocked are created in response to the initial flood of messages. Then, after the messages arrive, the anti-spam product is updated. Unfortunately, the spammers get the updates at the same time as the filter users. This enables the spammers to modify their message so that the next salvo will bypass even the newest filters.

A Bayesian filter learns to identify new spam the more it analyzes incoming e-mails. Using Bayesian filtering requires that you first train the mailer by showing it a bunch of mail that is junk, and a bunch of mail that is not. Then, you let it automatically classify new mail for you, and you continue to correct it as it makes mistakes.

3) The Bayesian technique is sensitive to the user and is difficult to fool. The Bayesian technique learns the email habits of the company and understands that. It let each user define spam so that the filter is highly personalized. Bayesian filters also automatically update and are self-correcting as they process new information and add it to the database. If an advanced spammer wants to trick a Bayesian filter spammer, it would have to know the email profile of each recipient. Because the Bayesian filter is customized by individual users, a spammer can never hope to gather this kind of information from every intended recipient.

4) The Bayesian method is multi-lingual and international. A Bayesian anti-spam filter, being adaptive, can be used for any language required. Most keyword lists are available in English only and are therefore quite useless in non English-speaking regions. The Bayesian filter also takes into account certain languages deviations or the diverse usage of certain words in different areas, even if the same language is spoken. This intelligence enables such a filter to catch more spam.

Why Spam Filter Express is the Best?

With more and more people use email as the everyday communication tool, there are more and more spams, viruses, phishing and fraudulent emails sent out to our email Inbox. Several email systems use filtering techniques that seek to identify emails and classify them by some simple rules. However, these email filters employ conventional database techniques for pattern matching to achieve the objective of junk email detection. There are several fundamental shortcomings for this kind of junk email identification technique, for example, the lack of a learning mechanism, ignorance of the temporal localization concept, and poor description of the email data.

Spam Filter Express is a powerful spam filter quickly identifies and separates the hazardous and annoying spam from your legitimate email. Based on Bayesian filtering technology, Spam Filter Express adapts itself to your email automatically, filtering out all of the junk mail with close to 100% accuracy. No adding rules, no complex training, no forcing your friends and colleagues to jump through hoops to communicate with you.

There are more and more anti spam tools are using the Bayesian filtering technology. Are all Bayesian filters the same? The answer is No. There is no industry standard for a Bayesian anti spam filter and the Bayesian mathematical formulas are well known and understood by mathematicians. But how Bayesian filters are implemented is different from one anti spam tool to another and is critical to success. For example, one of the key critical success factors for Bayesian filters is the source of your examples.

If spam can only be defined by examples, the quality of the examples used to create the definition is very important. If the samples are not representative of the type of email that you receive, as can be the case with some filters, you may not get accurate results.

Generally, there are two factors to consider: the initial start-up and continual learning.

• Startup: The results of Bayesian systems vary significantly at start-up, based on the initial definition of spam. Some filters come with a preprogrammed set of "spam models" that are the same from user to user. If they are not modified, such systems always result in a high error rate, as each person's definition of spam is different.Our spam filtering system combines the two techniques to create the most accurate "out of the box" experience for most users. These systems base the filters on your own email messages, but also add a database of carefully selected statistics if there are not enough spam messages. This lets the filters cover a broad range of spam collected over a long period.

• Continual Adaptation: While all Bayesian filters are based on examples, the best continually update the filters because these are able to learn from their mistakes. In this way, they do not need to wait for an update from a central source and they can immediately adapt to new types of spam. The process for continual learning is as follows: If the spam filter mistakes a spam message as good, the user has an easy way to identify it. The best filters then immediately update all of the relevant information used to analyze all future messages. In this way, the best messages are not likely to make the same mistake in the future. Even further, the best spam filters can become more accurate without user interaction just by processing new spam as it arrives. For example, a new type of spam message may arrive. Since it is new, a Bayesian filter may calculate that it is 90% similar to spam messages it has already seen. In this case, it would identify the message as spam because it is so much like known spam. To take it one step further, the filter can also learn about the new type of spam from the new message as it enters the spam folder. This enables the best filters to automatically adapt to new types of spam without updates from a centralized server.