To print: Click here or Select File and then Print from your browser's menu

This story was printed from silicon.com, located at http://www.silicon.com/

Story URL: http://www.silicon.com/publicsector/0,3800010403,39169629,00.htm


Brunel University uses spam filter to fight cyber bullying
Case study: 'Bad' words detected in many languages

By Julian Goldsmith

Published: Friday 11 January 2008

Brunel University has adapted its spam filter to help fight email bullying.

Based in the west of London, the university is one of the main higher education centres in the city and uses a distributed email system.

The system receives five million emails a week, much of it spam. As policy development and quality manager at the university's computer centre, it's Ian Liddell's job to make sure spam is automatically filtered out, without blocking any important correspondence between academics at the college and others elsewhere.

The system Brunel uses to screen spam, supplied by Secure Computing, is flexible enough to be used for other tasks in addition to filtering - including detecting email bullying.

In 2005 a young Korean student complained she was being harassed by someone sending out obscene emails in Korean using freemail accounts containing her name on the internal college email network. The bully succeeded in sending over 150 malicious emails before they were finally caught.

Liddell said: "These emails looked like they were coming from this student, but they contained messages that she found offensive, including death threats. We have a duty of care to all of our students to make sure the college networks aren't being used in an abusive way to any of them."

Security from A to Z

Click on the links below to find out more...

A is for Antivirus
B is for Botnets
C is for CMA
D is for DDoS
E is for Extradition
F is for Federated identity
G is for Google
H is for Hackers
I is for IM
J is for Jaschan (Sven)
K is for Kids
L is for Love Bug
M is for Microsoft
N is for Neologisms
O is for Orange
P is for Passwords
Q is for Questions
R is for Rootkits
S is for Spyware
T is for Two-factor authentication
U is for USB sticks/devices
V is for Virus variants
W is for Wi-fi
X is for OS X
Y is for You
Z is for Zero-day

The email filtering system checks through each message according to a profile of recognised words and phrases and decides whether each of them is about proper college business - at a fraction of the time it takes to do manually. Liddell explained a set of rules, or dictionary, has to be built up that defines the 'DNA' of bona fide messages at Brunel.

The more messages that are approved or held by the system, the more it automatically refines this profile and becomes more selective about what it decides are suspect messages. Liddell decided this system could be adapted to filter out abusive as well as spam emails.

The email filtering system allowed Liddell to construct a specific dictionary of Korean words that it could use to flag up potentially abusive emails for this student and hold them for her to confirm their validity, before sending them on.

By isolating the offending emails, the perpetrator was quickly apprehended, although no prosecution was brought.

Because the system is so precise, Liddell is also using it to comply with Freedom of Information (FoI) enquiries and data protection issues. If anyone at the college receives a message with an enquiry covered by FoI regulations, the system is designed to flag it up. This means the enquiry can be caught and answered within the 20 working days allowed.

The system is also being used to help the college comply with data protection regulations concerning students. It looks for any personal information such as student ID numbers in outbound emails that shouldn't be sent outside of the college network.


Quick Sitemap Links: