Case Study: Taking Spam Off the Radar

Unless you’re in a throwback profession, say working on a lobster boat or picking coffee

beans on the side of a tropical mountain, your business performance is suffering because of

a common 21st-century problem: spam.

While experience and common sense tell us that spam is a nuisance, what is less obvious is

that dealing with spam costs your business money, threatening your bottom line.

Consider this — according to a recent report from Nucleus Research, the average employee

receives a little more than 13 junk e-mails per day, which translates into six and a half

minutes spent dealing with spam each and every day. While that may not sound like much, the

time adds up, day by day, and when you multiply those costs across your business, the

damage is staggering.

Nucleus estimates that businesses lose an average of $874 per employee per year due to the

lost productivity related to handling spam. That means that for every 72 employees, a

company loses the equivalent of at least one employee’s services for the year.

Executives at Salzburg Airport Ltd., a regional airport located in the Austrian city where

Wolfgang Amadeus Mozart was born, decided that they couldn’t afford to that much employee

time. The airport employs approximately 250 people. If you plug that figure into Nucleus’

equation, the airport loses the productivity of about three and a half employees every year

to spam.

To deal with this problem, Salzburg Airport executives turned to Internet Security Systems,

a network security company based in Atlanta, Ga., to provide spam and web-content filtering

solutions.

Retaining their Uniqueness

At the Salzburg Airport, which serves about 1.3 million passengers per year, an employee’s

most important task is maintaining a high level of customer satisfaction. In fact, one of

the key ways regional airports compete with larger hubs is by providing a better customer

experience.

But how can your employees serve customers if they are buried under mountains of spam?

Airport executives knew that if they didn’t deal with the problem, its service would suffer

and the airport would risk becoming as impersonal as the larger airports it competes with.

Salzburg Airport has a unique network. Its 250 employees access the Web and email via

thin-client terminals, which accounts for 70 percent of all their computer stations. The

Windows XP server environment sits behind a NetScreen firewall, and Trend Micro is used for

anti-virus protection. Employees use Microsoft Exchange for email, and the airport even has

three Wi-Fi radio access points on the network.

”We consider spam as much more than a simple nuisance,” says Thomas Knauseder, manager of

IT security for the airport. Because of its impact on our network, we consider spam a

security issue.”

As the amount of junk mail arriving in employees’ inboxes grew dramatically, the network

slowed down and so did employee productivity. Plus, in a thin-client environment, computing

resources, including storage, are shared. That means that spam has an even greater effect

on the network.

”We knew we had a growing problem, and we determined that spam was the second most

pressing issue facing our IT staff, ranking right behind virus and intrusion concerns,”

says Knauseder, who also notes that spam often includes malicious content that can cause

far more trouble than just annoying the administrator and employees.

After considering several products, IT managers at the airport selected ISS’ Proventia Mail

Filter because of its low rate of false positives, its accuracy, and ease of use.

”Proventia Mail was installed and set up in a single day,” says Knauseder. ”It helps us

to diminish the increasing flood of spam. And due to the success of this product, we are

planning to use additional features of Proventia in the future.”

Continue on to the next page to find out how quickly the solution started to work.

Knauseder says Proventia Mail began stemming the flow of spam from day one. Based on six

different email analysis processes, Proventia Mail is able to filter out unsolicited spam,

while also protecting users from junk mails with dangerous attachments that could contain

viruses.

Using 10 different mail classifiers, the Proventia solution begins with a spam database

that contains more than 200,000 spam samples. The mail filter recognizes the slightest

variation of junk mail, providing end users with updates four times a day. Most types of

unwanted spam have one characteristic in common: URL links. Because junk mail is all about

advertisements, they must lead readers to a place where a sales transaction can be made,

and that place is typically a Web site.

When Proventia Mail Filter encounters a URL, it checks that Web address against the

vendor’s database to see whether it comes from a legitimate source or a source of spam.

For those messages that make it through this first layer of defense, they must then face

keyword analysis, a statistical online classifier, heuristic methods, and a check of the

sender’s email address against a database of known addresses.

Since the implementation of Proventia Mail Filter, the airport’s spam problem has been

dramatically reduced.

”Proventia blocked more than 15,000 junk mails in the first three months alone,”

Knauseder says.

Knauseder notes that with this mail filter Salzburg Airport was able to improve the working

environment for employees and protect them from the dangers connected with junk mail. Now

its 250 employees are no longer distracted by spam that is disguised as legitimate e-mail,

and no one wastes time purging spam from inboxes. All that attention now goes where it

belongs — to customer service.

RELATED NEWS AND ANALYSIS

• Ethics and Artificial Intelligence: Driving Greater Equality

  FEATURE |  By James Maguire,
  December 16, 2020

• AI vs. Machine Learning vs. Deep Learning

  FEATURE |  By Cynthia Harvey,
  December 11, 2020

• Huawei’s AI Update: Things Are Moving Faster Than We Think

  FEATURE |  By Rob Enderle,
  December 04, 2020

• Keeping Machine Learning Algorithms Honest in the ‘Ethics-First’ Era

  ARTIFICIAL INTELLIGENCE |  By Guest Author,
  November 18, 2020

• Key Trends in Chatbots and RPA

  FEATURE |  By Guest Author,
  November 10, 2020

• Top 10 AIOps Companies

  FEATURE |  By Samuel Greengard,
  November 05, 2020

• What is Text Analysis?

  ARTIFICIAL INTELLIGENCE |  By Guest Author,
  November 02, 2020

• How Intel’s Work With Autonomous Cars Could Redefine General Purpose AI

  ARTIFICIAL INTELLIGENCE |  By Rob Enderle,
  October 29, 2020

• Dell Technologies World: Weaving Together Human And Machine Interaction For AI And Robotics

  ARTIFICIAL INTELLIGENCE |  By Rob Enderle,
  October 23, 2020

• The Super Moderator, or How IBM Project Debater Could Save Social Media

  FEATURE |  By Rob Enderle,
  October 16, 2020

• Top 10 Chatbot Platforms

  FEATURE |  By Cynthia Harvey,
  October 07, 2020

• Finding a Career Path in AI

  ARTIFICIAL INTELLIGENCE |  By Guest Author,
  October 05, 2020

• CIOs Discuss the Promise of AI and Data Science

  FEATURE |  By Guest Author,
  September 25, 2020

• Microsoft Is Building An AI Product That Could Predict The Future

  FEATURE |  By Rob Enderle,
  September 25, 2020

• Top 10 Machine Learning Companies 2021

  FEATURE |  By Cynthia Harvey,
  September 22, 2020

• NVIDIA and ARM: Massively Changing The AI Landscape

  ARTIFICIAL INTELLIGENCE |  By Rob Enderle,
  September 18, 2020

• Continuous Intelligence: Expert Discussion [Video and Podcast]

  ARTIFICIAL INTELLIGENCE |  By James Maguire,
  September 14, 2020

• Artificial Intelligence: Governance and Ethics [Video]

  ARTIFICIAL INTELLIGENCE |  By James Maguire,
  September 13, 2020

• IBM Watson At The US Open: Showcasing The Power Of A Mature Enterprise-Class AI

  FEATURE |  By Rob Enderle,
  September 11, 2020

• Artificial Intelligence: Perception vs. Reality

  FEATURE |  By James Maguire,
  September 09, 2020