Scribd
Upload
25 views13 pages

Malware Final

Uploaded by

Sanjana.S
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
25 views13 pages

Malware Final

Uploaded by

Sanjana.S
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 13

S J C INSTITUTE OF TECHNOLOGY

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING


The Project work Synopsis Review

“ML-Based Cross-Platform Malware Detection”


PRESENTED BY

Bindhu Shree G V 1SJ20CS027


Chandan Gowda N 1SJ20CS032
Sanjana S 1SJ20CS128
Shwethashree K V 1SJ20CS140
UNDER THE GUIDANCE OF
Prof. Bhavya R A Dr. Shrihari M R Dr. Seshaiah M Dr. Harshavardana Dr. Manjunatha
Doddamani Kumar B H
Assistant Professor Associate Professor Associate Professor Associate Professor Professor and HOD
CSE, SJCIT CSE, SJCIT CSE, SJCIT CSE, SJCIT CSE, SJCIT
CONTENTS

I. ABSTRACT
II. INTRODUCTION
III. PROBLEM DOMAIN AND PROBLEM STATEMENT
IV. STUDY OF THE EXISTING SYSTEMS AND FEASIBILITY OF PROJECT PROPOSAL
V. OBJECTIVES OF THE PROPOSED WORK
VI. OUTCOMES OF THE PROPOSED WORK
VII. METHODOLOGY
VII. PLANNING OF THE PROJECT WORK

Dept. of CSE, SJCIT 2


ABSTRACT

One of the most significant issues facing internet users nowadays is malware. Malware is any
software intentionally designed to cause damage to a computer, server, client, or computer
network. A wide variety of malware types exist, including computer viruses, worms, Trojan
horses, ransomware, spyware, adware, rogue software, wiper and scareware. Polymorphic
malware is a new type of malicious software that is more adaptable than previous generations
of viruses. Machine learning algorithms can be used to detect malware by identifying its
behaviour and other characteristics.

Dept. of CSE, SJCIT 3


INTRODUCTION

Malware is a major threat to the security of computer systems and networks.


Cyberattacks are currently the most pressing concern in the realm of modern technology.
Malware is an example of a cyberattack. Malware is any program or set of instructions
that is designed to harm a computer, user, business, or computer system. Machine
learning (ML) algorithms have the potential to overcome these limitations by detecting
malware based on its behaviour and other characteristics.

Dept. of CSE, SJCIT 4


PROBLEM DOMAIN
Malware detection involves using machine learning (ML) techniques to identify and
classify malicious software (malware) that can run on different operating systems or
platforms.

Key Aspects of the Problem Domain:

❑ Cross-Platform Compatibility

❑ Data Diversity

❑ Anomaly Detection

❑ Real-time Detection

Dept. of CSE, SJCIT 5


PROBLEM STATMENT

❑ In today's interconnected digital landscape, the proliferation of malware poses a


significant threat to the security and privacy of individuals and organizations.

❑ Malicious software not only targets a variety of operating systems (e.g., Windows,
macOS, Android, iOS) but also continuously evolves to evade traditional signature-
based detection methods.

❑ Consequently, there is an urgent need for a robust and adaptive malware detection
system that can effectively identify and classify malware across diverse platforms.
STUDY OF THE EXISTING SYSTEMS AND FEASIBILITY OF
PROJECT PROPOSAL
SL PAPER TITLE DISCUSSION REMARKS
NO
1 M.S,Akhtar; Tao Feng The paper explores various It highlights the challenge of
“Malware Analysis and approaches and techniques, such as polymorphic malware, which
Detection Using Machine static analysis and feature constantly modifies its signature
LearningAlgorithms (2022)” extraction, to identify and classify traits to evade traditional
malware using machine learning detection models.
models.
2 Akshit Kamboj, Priyanshu The author also mentions future The author also mentions future
Kumar, Amit Kumar Bairwa , work, which includes trying work, which includes trying
“Detection of malware in different machine learning models, different machine learning models,
downloaded files using various improving prediction accuracy, and improving prediction accuracy,
machine learning models exploring new techniques. and exploring new techniques.
(2022)”

Dept. of CSE, SJCIT 7


STUDY OF THE EXISTING SYSTEMS AND FEASIBILITY OF
PROJECT PROPOSAL
SL PAPER TITLE DISCUSSION REMARKS
NO
3 Souri, Hosseini Hum,“A The author's discussion in the Using machine learning models
State-Of-The-Art survey Of article is about expanding malware for malware detection is time-
Malware Detection detection approaches in new consuming compared to standard
Approaches Using platforms and architectures such as methods due to the complexity of
Datamining Internet of Things (IoT) the malware dataset.
Techniques(2018) applications, e-banking, and social
networks
4 Raj Sinha, “Study Of Malware In this paper, we explore the And as per the accuracy of the
Detection Using Machine various different types of the results we found that the Malware
Learning” models which are used by various detection based on the neural
researchers in the malware networks are more effective and
detection thereby highlighting the accurate as compared to the other
accuracy of these models. approaches.

Dept. of CSE, SJCIT 8


OBJECTIVES OF THE PROPOSED WORK
❑ To investigate on how to implement machine learning to malware detection in order
to detection unknown malware.

❑ To develop a malware detection software that implement machine learning to detect


unknown malware.

❑ To validate that malware detection that implement machine learning will be able to
achieve a high accuracy rate with low false positive rate.

❑ To effectively Detecting malware in specific types of files, such as executable files,


PDFs, or images.

Dept. of CSE, SJCIT 9


OUTCOMES OF THE PROPOSED WORK

❑ Improved ability to detect new and emerging malware strains.

❑ Prevent user from entering malicious websites.

❑ Improved detection accuracy.

❑ Reduced false positive rate.

❑ Improved ability to detect new and emerging malware strains.

Dept. of CSE, SJCIT 10


METHODOLOGY
The Methodology to implement the following steps :

❑ Dataset

❑ Pre-Processing

❑ Features Extraction

❑ Features Selection

Dept. of CSE, SJCIT 11


PLANNING OF THE PROJECT WORK
THANK YOU

Dept. of CSE, SJCIT 13

You might also like