Online Banking With Fraud Detecting
ABSTRACT
This survey attempts to provide a comprehensive and structured overview of the existing
research for the problem of detecting anomalies in discrete sequences. The aim is to
provide a global understanding of the sequence anomaly detection problem and how
techniques proposed for different domains relate to each other. Our specific contributions
are as follows: We identify three distinct formulations of the anomaly detection problem,
and review techniques from many disparate and disconnected domains that address each
of these formulations. Within each problem formulation, we group techniques into
categories based on the nature of the underlying algorithm. For each category, we provide
a basic anomaly detection technique, and show how the existing techniques are variants
of the basic technique. This approach shows how different techniques within a category
are related or different from each other. Our categorization reveals new variants and
combinations that have not been investigated before for anomaly detection. We also
provide a discussion of relative strengths and weaknesses of different techniques. We
show how techniques developed for one problem formulation can be adapted to solve a
different formulation; thereby providing several novel adaptations to solve the different
problem formulations. We highlight the applicability of the techniques that handle
discrete sequences to other related areas such as online anomaly detection and time series
anomaly detection.
EXISTING SYSTEM:
Even though the existing techniques appear to have the same objective, i.e., to detect
anomalies in discrete sequences, a deeper analysis reveals that different techniques
actually address different problem formulations. An Anomaly based intrusion detection
system, is a system for detecting computer intrusions and misuse by monitoring system
activity and classifying it as either normal or anomalous. This anamoly detection based
on intrusion was not efficient as earlier. So we propose anomaly detection for discrete
sequences is a challenging task in which to detects anomalous events within a sequence
might not be directly applicable to detecting anomalies that are caused by a subsequence
of events occurring together. The experimental results have shown that the system can
detect anomalous user activity effectively.
PROPOSED SYSTEM:
A security analyst is interested in detecting “illegal” user sessions on a computer
belonging to a corporate network. An illegal user session is caused when an unauthorized
person uses the computer with malicious intent. To detect such intrusions, the analyst can
use the first formulation, in which the past normal user sessions (sequence of system
calls/commands) are used as the training data, and a new user session is tested against
this training data. The world of online banking this typically means detecting unusual (or
suspicious) online banking behavior in order to identify account takeover and fraudulent
transactions. Examples of what anomaly detection could identify include
Accessing
online banking from an unusual location or at an usual time of day.
Using
online banking features not typically used.
Using
online banking feature in an unexpected sequence.
Changing
personal information.
Adding
payees.
Adding
approvers or changing approval limits
Types
and amounts of transactions
MODULE DESCRIPTION:
Number of Modules
After careful analysis the system has been identified to have the following modules:
1. Authenticated User Module.
2. Online Anamoly Detection Module.
3. Intrusion Detection Module.
4. Automated Response Module.
1. Authenicated User Module:
Online banking platforms have all the data needed for anomaly detection. In that data is
the unique online banking DNA for each individual account holder their patterns of
online banking behavior. The individual behavior such as their login location, finance
management and account maintenance and money transactions.
2. Online Anamoly Detection Module:
Online anomaly detection has the advantage that it can allow analysts to undertake
preventive or corrective measures as soon as the anomaly is manifested in the sequence
data. A technique that detects anomalous events within a sequence might not be directly
applicable to detecting anomalies that are caused by a subsequence of events occurring
together. Anomaly detection is a proven approach to defending against the array of
threats facing online banking. This anomaly detection has been so successful at stopping
online fraud.
3. Intrusion Detection Module:
A security analyst is interested in determining if the frequency with which a user
executed a particular sequence of commands is higher (or lower) than an expected
frequency. The sequence login, passwd, login, passwd corresponds to a failed login
attempt followed by a successful login attempt. Occurrence of this sequence in a user’s
daily profile is normal if it occurs occasionally, but is anomalous if it occurs very
frequently, since it could correspond to an unauthorized user surreptitiously attempting an
entry into the user’s computer by trying multiple passwords. To detect such intrusions,
the analyst can use the third formulation, in which the sequence of commands is the
query pattern, and the frequency of the query pattern in the user sequence for the given
day is compared against the expected frequency of the query pattern in the daily
sequences for the user in the past, to detect anomalous behavior.
4. Automated Response Module:
Response to anomalies is automated or performed by staff. Proactive response stops
criminals in their tracks AND builds trust with account holders. The staffs immediately
hold their particular persons account and stop payments. They give alert notification
immediately through mail or mobile that some intrusion is going to happen. Detects the
widest range of malware and non-malware fraud attacks. Automatically monitors all
clients on all devices, including computers, smartphones, and tablets. Monitors every
online and mobile banking session for fraudulent login, reconnaissance, fraud setup, and
anomalous transactions.
SOFTWARE REQUIREMENTS:
Operating System
: Windows
Technology
: Java and J2EE
Web Technologies
: Html, JavaScript, CSS
IDE
: My Eclipse
Web Server
: Tomcat
Tool kit
: Android Phone
Database
: My SQL
Java Version
: J2SDK1.5
HARDWARE REQUIREMENTS:
Hardware
:
Pentium
Speed
:
1.1 GHz
RAM
:
1GB
Hard Disk
:
20 GB
Floppy Drive
:
1.44 MB
Key Board
:
Standard Windows Keyboard
Mouse
:
Two or Three Button Mouse
Monitor
:
SVGA
Process Flow: