---------------------------------------------------------------------
Speaker:        Dr. Dit Yan YEUNG
                Associate Professor
                Department of Computer Science
                The Hong Kong University of Science & Technology

Topic:          "Intrusion Detection Research: Artificial Intelligence
                 Meets Computer Security"

Date:           Monday, 29 April 2002

Time:           4:00pm - 5:00pm

Venue:          Lecture Theater F
                (Leung Yat Sing Lecture Theater, near lift nos. 25/26)
                HKUST

ABSTRACT:

The price to pay for the convenience brought about by a high degree of
connectivity through computer networks is the increased vulnerability of
computers to attacks by intruders.  As attacks become more and more
sophisticated, it is simply impossible to ensure that a computer or a
networked computing environment is entirely free from intrusive
activities. A more realistic approach to take is to assume that intrusions
do occur, but to attempt to detect their occurrence with minimal delay so
that appropriate, timely actions could be taken to minimize the damage.
There are two types of intrusion detection systems.  Host-based systems
detect possible attacks into individual host computers, while
network-based systems monitor network behavior by examining the content
and format of network traffic data.

In this talk, we will first formulate intrusion detection as a pattern
classification problem.  Unlike many previous works in this area, we will
formulate the problem as a novelty detection problem so that intrusion
data, which typically are more difficult to collect than normal data, are
not required for classifier training.  We will then present three
different experiments.  Two experiments are for host-based intrusion
detection.  The first one learns program profiles based on Unix system
calls and the second one learns user profiles based on Unix shell
commands. The third experiment is for network-based intrusion detection
based on monitoring TCP/IP packet sequences.  Time permitting, some
possible research directions will be discussed.

(This talk is based on joint work with Calvin Chow and Yuxin Ding.)



*****************
Biography:

Dit-Yan Yeung received his BEng degree in electrical engineering and MPhil
degree in computer science from the University of Hong Kong (HKU), and his
PhD degree in computer science from the University of Southern California
(USC) in Los Angeles.  He started his academic career as an assistant
professor at the Illinois Institute of Technology (IIT) in Chicago. He
then joined HKUST and is currently an associate professor in the
Department of Computer Science.  He is also Director of the Sino Software
Research Institute (SSRI).

His current research interests include the theoretical aspects of machine
learning and pattern recognition as well as their applications in
handwriting recognition, computer security, biometrics, and data mining
problems.


                For enquiries, please call 2358 7008
                  **** ALL are Welcome ****
--------------------------------------------------------------------------