Data Mining for Security
Applications
1
August 20, 2018
C Contents of the Presentation
S
E
D
Intrusion Detection
1. Over View of Data Mining
M
N 2. Cyber Security and Data Mining
N
I 3. Intrusion Detection
T
4. Data Mining For Information Security / Digital Forensics
A
L 5. Conclusion
L
A
H
A
B
A
D
August 20, 2018 2
C Data Mining
S
E
D
• Data Mining - Extraction of interesting information or
M patterns from data in large databases [Han and Kamber
N 2005].
N
I
T • Data mining is used to sort through the tremendous
amounts of data stored by automated data collection tools.
A
L • Extracts rules, regularities, patterns, and constraints from
L databases.
A
H
A
B
A
D
August 20, 2018 3
C Threats
S
E
D
M
N
N
I
T
A
L
L
A
H
A
B
A
D
August 20, 2018 4
C Data Mining For Cyber Security
S
E
D
I
Data mining is being applied to problems such as intrusion detection
M
N and auditing. For example
N
I 1. Anomaly detection techniques could be used to detect unusual
T patterns and behaviors.
A 2. Classification may be used to group various cyber attacks and
L
L then use the profiles to detect an attack when it occurs.
A
H 3. Prediction may be used to determine potential future attacks
A depending in a way on information learnt about terrorists
B
A through email and phone conversations
D
August 20, 2018 5
C Intrusion Detection
S
E
D
I
Data mining can help automate the process of investigating intrusion
M
N detection alarms.
N
I
T Data mining on historical audit data and intrusion detection alarms can
A reduce future false alarms.
L
L
A
H
A
B
A
D
August 20, 2018 6
C Data Mining for Counter
S
E
Terriorism
D
M
N
N
I
T
A
L
L
A
H
A
B
A
D
August 20, 2018 7
Data Mining for Surveillance
Huge amounts of surveillance
and video data available in the
security domain
Analysis is being done off-line
usually using “Human Eyes”
Need for tools to aid human
analyst ( pointing out areas in
video where unusual activity
occurs)
8
August 20, 2018
C
S
E
D
M
N
N
I
T
A
Thanks
L
L
A
H
A
B
A
D 9
August 20, 2018