Clement Machine Learning Methods For Malware Recognition Based On Semantic Behaviours

You might also like

Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 5

Domain: Deep Learning

Technology: Python

CLEMENT MACHINE LEARNING METHODS FOR MALWARE


RECOGNITION BASED ON SEMANTIC BEHAVIOURS

ABSTRACT:

Security breaches due to attacks by malicious software (malware) continue to escalate posing a
major security concern in this digital age. With many computer users, corporations, and
governments affected due to an exponential growth in malware attacks, malware detection
continues to be a hot research topic. Driven by the substantial profits behind cybercrimes, the
amount of new variants of malware has experienced unprecedented growth.Various malware has
been widely used for cyber-criminals to accomplish their evil intentions and goals. To combat
the increasing amount and reduce the threat of malicious programs, a novel deep learning
framework, which uses NLP techniques for reference, combines CNN and LSTM neurons to
capture the locally spatial correlations and learn from sequential long-term dependency is
proposed.

KEYWORDS: Machine Learning, Computer Security, Malware Recognition, CNN, LSTM,


Natural Language Processing (NLP).
Domain: Deep Learning
Technology: Python

EXISTING SYSTEM:

Older techniques like Logistics Regression, Decision Trees, Support vector machine are
extensively used for malware recognition in software’s. Such system is easy to implement they
depend a lot of the developers understanding of the software and malware domain in order to
fine tune it. Even many Neural Networks based software recognition system exists but they fail
to consider the semantic behaviors.

DISADVANTAGES:

 Low accuracy.
 Cannot be scaled beyond a point.
 Higher complexities.
 Fails to consider semantic behaviors.

PROPOSED SYSTEM:

Malware represents any software which access the system without the permission of the user or
administration. To combat this, we propose a system using CNN and LSTM for malware
recognition. It also uses NLP for reference in order to improve recognition based on semantic
behaviors.
Domain: Deep Learning
Technology: Python

BLOCK DIAGRAM:

ADVANTAGES:

 Higher accuracy.
 Can be heavily scaled.
 Low complexities.
 Considers semantic behaviors.

APPLICATIONS:

 Government agencies can use this application to protect their top secret documents.
 Companies can protect their patents, confidential information from spammers.

SYSTEM SPECIFICATIONS:
Domain: Deep Learning
Technology: Python
H/W SPECIFICATIONS:
 Processor - I3/Intel Processor
 RAM - 4GB (min)
 Hard Disk - 128 GB
 Key Board - Standard Windows Keyboard
 Mouse - Two or Three Button Mouse
 Monitor - Any

S/W SPECIFICATIONS:
• Operating System : Windows 7+
• Server side Script : Python 3.6+
• IDE : PyCharm
• Libraries Used : Pandas, TensorFlow, Matplotlib, Seaborn, NLTK.

LEARNING OUTCOMES:
 Uses of Unsupervised Learning.
 Importance of classification.
 Scope of malware detection.
 Use of NLP techniques.
 Importance of PyCharm IDE.
 How CNN works.
 Difference between LSTM and RNN.
 Process of debugging a code.
 Input and Output modules.
 How test the project based on user inputs and observe the output?

 Project Development Skills:

o Problem analyzing skills.


o Problem solving skills.
o Creativity and imaginary skills.
o Programming skills.
Domain: Deep Learning
Technology: Python
o Deployment.
o Testing skills.
o Debugging skills.
o Project presentation skills.
o Thesis writing skills.

You might also like