Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd Logo
Upload

Welcome to Scribd!

  • 5 views

    Ransomware Detector Using Deep Learning: Objective

    Uploaded by

    chhayankritu

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd

    Ransomware Detector Using Deep Learning: Objective

    Uploaded by

    chhayankritu
    5 views5 pages

    Original Title

    162918334075

    Copyright

    © © All Rights Reserved

    Available Formats

    DOCX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    5 views5 pages

    Ransomware Detector Using Deep Learning: Objective

    Uploaded by

    chhayankritu

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    of 5

    Technology: Python

    Domain: Machine
    Learning

    RANSOMWARE DETECTOR USING DEEP LEARNING

    OBJECTIVE:

    The main goal of this analysis study is detecting Ransomwares in software


    compare the algorithm which algorithm provide high accuracy. Finally select
    the best algorithm to predict the stock price at early stage.

    ABSTRACT:

    This project demonstrates a novel approach to detecting ransomware targeted at


    Microsoft Windows, combining 2 deep learning neural network classifiers to
    create an ensemble, taking files as input in Microsoft’s standard PE file format,
    such as those with a ‘.exe’ file extension, and returning a prediction of the file
    belonging to 1 of 3 classes: benign, generic malware, or ransomware. The
    model’s ability to distinguish between ransomware and other forms of malware
    allows it to be applied as an extension to an existing malware detection system
    such as anti-virus software, and aid in the categorisation and reverse
    engineering of new in-the-wild ransomware samples. The ensemble automates
    static analysis of Windows software binaries by extracting features from the
    contents of the files and abstracting patterns within these features. The results of
    testing the ensemble model on data not seen in its training suggest a high level
    of predictive power in classifying new in-the-wild samples.

    KEYWORDS: Ransomware, Malware, Windows.


    Technology: Python
    Domain: Machine
    Learning

    EXISTING SYSTEM:

    Traditional ml algorithms basically use observations to estimate predictions.


    Traditional practices fail to detect this type of ransomwares. Machine Learning
    have different types of algorithms and each has its own structure of working
    procedure which contains different intuitions. In these intuitions, models are
    working on different procedures in different ways and also delivers high and
    less accuracies. The major challenge is to create a model for them so that no one
    have less accuracy. In this existing system we used ANN & Logistic regression
    which results less accuracy. Such a models won’t be able to match with our
    requirements and it also consumes more time.

    DISADVANTAGES:

     Low efficiency.
     Time consuming.
     Expensive.
     High complexities.

    PROPOSED SYSTEM:

    We propose this application that can be considered a useful system since it


    helps to reduce the limitations obtained from KNN and Logistic Regression. By
    providing support through the regression analysis, it can be able to generate best
    results for attributes without any overlap. The system is developed in a Flask
    based Python environment. MySQL is used for database management and the
    models involved in this application are artificial neural network ANN.

    BLOCK DIAGRAM:
    Technology: Python
    Domain: Machine
    Learning

    ADVANTAGES:

     High efficiency.
     Time Saving.
     Inexpensive.
     Low complexities.

    SYSTEM SPECIFICATIONS:
    Technology: Python
    Domain: Machine
    Learning

    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, Numpy, Scikit-Learn

    LEARNING OUTCOMES:

     About Python.
     About Pandas.
     About Numpy.
     About Machine Learning.
     About Artificial Intelligent.
     About how to use the libraries.
     Virtualization.
     About future outcomes for the stock prices.
     About how to generate the predictions with python code.
     Project Development Skills:

    o Problem analyzing skills.


    Technology: Python
    Domain: Machine
    Learning

    o Problem solving skills.


    o Creativity and imaginary skills.
    o Programming skills.
    o Deployment.
    o Testing skills.
    o Debugging skills.
    o Project presentation skills.
    o Thesis writing skills.

    You might also like