Scribd
Upload
3K views38 pages

Modeling and Predicting Cyber Hacking Breaches: Under The Guidance Of: Team Members

The document discusses modeling and predicting cyber hacking breaches. It analyzes a dataset of cyber incident breaches from 2005-2017. It classifies the data using machine learning algorithms to identify malware attacks and predict different types of cyber attacks. The analysis finds that breach incident times and sizes are best modeled by stochastic processes, unlike previous literature. It also conducts qualitative and quantitative trend analysis on the dataset.

Uploaded by

srinikitha
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
3K views38 pages

Modeling and Predicting Cyber Hacking Breaches: Under The Guidance Of: Team Members

The document discusses modeling and predicting cyber hacking breaches. It analyzes a dataset of cyber incident breaches from 2005-2017. It classifies the data using machine learning algorithms to identify malware attacks and predict different types of cyber attacks. The analysis finds that breach incident times and sizes are best modeled by stochastic processes, unlike previous literature. It also conducts qualitative and quantitative trend analysis on the dataset.

Uploaded by

srinikitha
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 38

MODELING AND PREDICTING CYBER HACKING

BREACHES

TEAM MEMBERS: UNDER THE GUIDANCE OF:


K. Saipriyanka (16NP1A0520) Miss, P. Sarala.
B. Teja Sri (16NP1A0507) CSE Dept.
G. Sudharma (16NP1A0515)
SK. Mehanaz (16NP1A0548)
CONTENTS
 ABSTRACT
 INTRODUCTION
 OBJECTIVE
 ANALYSIS
 DESIGN
 TESTING
 OUTPUT SCREENSHOTS
 CONCLUSION
 FUTURE WORK
 REFERENCES
ABSTRACT
 Analyzing cyber incident data sets is an important method
for deepening our understanding of the evolution of the
threat situation.
 we report a statistical analysis of a breach incident data set
corresponding to 12 years (2005–2017) of cyber hacking
activities that include malware attacks.
 we show that, in contrast to the findings reported in the
literature, both hacking breach incident inter-arrival times
and breach sizes should be modeled by stochastic processes.
 we conduct both qualitative and quantitative trend analyses
on the data set.
INTRODUCTION
 Machine learning is a growing technology which enables
computers to learn automatically from past data.
 Machine learning uses various algorithms for building
mathematical models and making predictions using historical
data or information.
 Currently, it is being used for various tasks such as image
recognition, speech recognition, email filtering, Facebook
auto-tagging recommender system, and many more.
Classification of Machine Learning
At a broad level, machine learning can be classified into three
types:
1. Supervised learning
2. Unsupervised learning
3. Reinforcement learning
Why it is important?

 Machine learning has several very practical applications


that drive the kind of real business results – such as time
and money savings – that have the potential to
dramatically impact the future of your organization.
 At Interactions in particular, we see tremendous impact
occurring within the customer care industry, whereby
machine learning is allowing people to get things done
more quickly and efficiently.
OBJECTIVE

 Analysis of a breach incident data set


corresponding to 12 years (2005–2017) of cyber
hacking activities that include malware attacks.
 Classify the data set to know it is malware attack
or unmalware.
 Also to predict the various cyber hacking attacks.
ANALYSIS
EXISTING SYSTEM:
 Are data breaches caused by cyber-attacks increasing,
decreasing, or stabilizing?
 The dataset analyzed ,covered the time span from 2000 to 2008
and does not necessarily contain the breach incidents that are
caused by cyber-attacks.
 Two kinds of incidents: negligent breaches, malicious
breaches.
DISADVANTAGES:
 Mentioning the breach size.
 We don’t know how it was hacked.
PROPOSED SYSTEM:
 Breach incident data set corresponding to 12 years
(2005–2017) of cyber hacking activities that include malware
attacks.
 We show that both the hacking breach incident interarrival
times (reflecting incident frequency) and breach sizes.
 And also analysis the nine type of hacking attacks.

ADVANTAGES:
 Knowing the inter-arrival times and the breach sizes.
 Both qualitative and quantitative trend analyses of the cyber
hacking breach incidents.
SYSTEM REQUIREMENTS:
Software Requirements:
1. Python (3.6.2)
2. Django(1.11.5)
3. Mysql
4. Html , Css
5. Wampserver (2.4)
Hardware Requirements:
Processor: Pentium IV or higher.
RAM: 256 MB.
Space on Hard Disk: minimum 512MB
DESIGN
Architecture:
MODULES:
UPLOAD DATA:
 The data resource to database can be uploaded by both
administrator and authorized user.
 The data can be uploaded with key in order to maintain the
secrecy of the data that is not released without knowledge of
user.
ACCESS DETAILS:
 The access of data from the database can be given by
administrators.
 Uploaded data are managed by admin and admin is the only
person to provide the rights to process the accessing details and
approve or unapproved users based on their details.
USER PERMISSIONS:
 The data from any resources are allowed to access the data with
only permission from administrator.If user is access the data
with wrong attempts then, users are blocked accordingly.
 If user is requested to unblock them, based on the requests and
previous activities admin is unblock users.

DATA ANALYSIS:
 Data analyses are done with the help of graph.
 The collected data are applied to graph in order to get the best
analysis and prediction of dataset and given data policies.
ALGORITHM:
SUPPORT VECTOR MACHINE:
 “Support Vector Machine” (SVM) is a supervised machine
learning algorithm which can be used for both
classification and regression challenges.
 However, it is mostly used in classification problems.
 Here, it is used to classify the nine type of cyber hacking
attacks. Namely,

1.Man-in-the-middle Attack 6.Eavesdropping attack


2.Phishing and spear phishing attacks
3.Drive-by attack 7.Birthday attack
4.Password attack
5.Cross-site scripting (XSS) attack 8.Teardrop attack
9.SQL injection attack
CLASS DIAGRAM:
USER:

ADMIN:
SEQUENCE DIAGRAM:
a)User
b)Admin
COLLABORATION DIAGRAM

a)User
b)Admin
USE CASE DIAGRAM:
a)User
b)Admin
COMPONENT DIAGRAM:
a)User
b)Admin
DEPLOYMENT DIAGRAM:
a)User
b)Admin
ACTIVITY DIAGRAM:
a)User
b)Admin
DATA FLOW DIAGRAM:
a)User
b)Admin
ER DIAGRAM:
a)User
b)Admin
TESTING
UNIT TESTING:
 Unit testing involves the design of test cases that validate that
the internal program logic is functioning properly.
 That program inputs produce valid outputs.

INTEGRATION TESTING:
 Integration tests are designed to test integrated software
components to determine if they actually run as one program.
 Exposing the problems that arise from the combination of
components.
FUNCTIONAL TESTING:
 Functional tests provide systematic demonstrations.
 It mainly centers on valid input , invalid input , output.

SYSTEM TESTING:
 System testing ensures that the entire integrated software
system meets requirements.
OUTPUT SCREENSHOTS:
USER LOGIN

USER ADDDATA
MALWARE DATA:

UNMALWARE DATA:
ADMIN LOGIN:

BREACHES ANALYSIS:
GRAPHICAL ANALYSIS
CONCLUSION
 We analyzed a hacking breach dataset from the points of view
of the incidents inter-arrival time and the breach size, and
showed that they both should be modeled by stochastic
processes.
 And also we classify the nine type of attacks.

FUTURE WORK
 More research needs to be conducted towards understanding
the predictability of breach incidents.
 The statistical models developed in this project show
satisfactory fitting and prediction accuracies. The
methodology presented in this project can be adopted or
adapted to analyze datasets of a similar nature.
REFERENCES
 Z. Zhan, M. Xu, and S. Xu, “Characterizing honeypot-captured cyber
attacks: Statistical framework and case study,” IEEE Trans. Inf. Forensics
Security, vol. 8, no. 11, pp. 1775–1789, Nov. 2013.
 [23] Z. Zhan, M. Xu, and S. Xu, “Predicting cyber attack rates with
extreme values,” IEEE Trans. Inf. Forensics Security, vol. 10, no. 8,
pp. 1666–1677, Aug. 2015.
 C. Peng, M. Xu, S. Xu, and T. Hu, “Modeling and predicting extreme
cyber attack rates via marked point processes,” J. Appl. Stat., vol. 44,
no. 14, pp. 2534–2563, 2017.
 R. Sen and S. Borle, “Estimating the contextual risk of data breach: An
empirical approach,” J. Manage. Inf. Syst., vol. 32, no. 2, pp. 314–341,
2015.
THANK YOU

You might also like