Scribd
Upload
15 views

Cyber Security in Power Systems Using

Uploaded by

Sharmathi. R Sharmathi.R
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
15 views

Cyber Security in Power Systems Using

Uploaded by

Sharmathi. R Sharmathi.R
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/ 14

Cyber Security in Power

Systems Using Meta-Heuristic


and Machine
LearningAlgorithms By…
XXXX
abstract
 Now’s a day’s security is a feature or factor which is most important about any sector

which ensures the protection of data. It prevents unauthorized persons, thieves,


hackers, etc.
 In this field, there are three main feature which is essential for data security i.e.

confidentiality, integrity, availability, these three main features which prevent from
unauthorized any other third person.
 Confidentiality basically if we send the data from one person to another person then

only authorized person can access & integrity if we transfer the information from one
to another then no one can change.
 The availability of the resources should be available 24/7 hour or data should be

available on demand. Process of communication using Encryption and Decryption


over data.
 To convert the plain text into ciphertext is Encryption and convert the ciphertext into

plain text is Decryption and both methods called as a Cryptology. These processes
depend on two types of keys which is public key & private key
Introduction
 In today's generation, data security Most crucial factor which
can achieve by information security system. It protects from
unauthorized third person. In this information system, there are
main two process help to communicate from one person to
another person whit security.
 In earlier before we don't have any security system to protect the

data from unauthorized persons or hackers etc. At that time are


many possible chances to hack the information. Before this, a user
has to put extra effort to transform to information with security
because there are many chances to hack or leak that information.
 In today's generation, we have many algorithms or techniques to

prevent the data from unauthorized persons or hackers. In the


Aim
 The aim of this system is to arrive at a method for embedding information into

video files without affecting its original perception and also not giving any hint to
the intruder.
 The objectives are three fold.

i. Hiding the secret information in an AVI video file format

ii. Encryption to increase security

iii. Decryption and message recovery

iv. Reduce the stroage


EXISITNG SYSTEM
 This technique combines cryptography with steganography by first encrypting the

secret message and then hiding the encrypted secret message in the image.
 The integration of cryptography and steganography provides an additional layer of

security that ensures that the message is delivered securely and reliably to the
intended recipient.
Proposed system
 For embedding the secret data for the generation of the best pixels,

 Hybrid Neural network technique is used and for classifying the suitable regions in

the cover data, CNN (Convolutional Neural Networks), RNN(Recurrent Neural


Networks) is used as a classifier.
 Basically, this work has focussed on the security by using the combination of

decomposition technique with the machine learning methods for the enhancement of
the security rate in the realistic applications.
 Parameters like PSNR, MSE and entropy are used to check the effective results

being obtained after the execution of the simulation work.


Proposed system
Module 1
INPUT DATA STAGE -
 Data Acquisition The first stage of any vision system is the data acquiring stage.

 After the image has been obtained, different methods of processing can be put

into the image to carry out the many vision tasks be in need of today.
 If the data has not been obtained satisfactory, then the awful tasks may not be

achievable, even with the subvention of some form of data enhancement.


Module 2
 PRE-PROCESSING
 The pre-processing is the first step to prepare the video for the next stage.
 The preprocessing remove image errors, noise introduced during the scanning
and reading image, improving the quality of an image.
 The pre-processing steps involve color normalization, statistical method, and
convolution method.
Module 3
 BACKGROUND SUBTRACTION

 The background subtraction, is the method of removing the background image

from the real image for the purpose of video sequences processing become
simple.
 it is also known as foreground extraction and used for detecting the moving

object, the region of interest etc.


 After the background subtraction output image pixel is represented by O(x,y)

and the input image represented by I(x,y) and B(x,y) is used to represent for the
background image.
Module 4
 IMAGE SEGMENTATION

 Image segmentation is computer vision techniques in which groups sharing the

similar properties, for example, a group having same color pixels or border and
a common shape such as a line, circle or ellipse or polygon.
 Image segmentation further classified as edge detection, region-based
classification, thresholding, or any combination of these techniques.
Module 5
 CLASSIFICATION

 After the encryption part (segmentation module) the data is applied into block

chain with DBN algorithms to convert the entire files into ID.
 The results with the DBN algorithm and convert the video into text file to save

the best one in a database.


 If the user want to retrieve the original info based on the ID it will be retrieved
TOOLS USED
 MATLAB
 AWS – mediator
 GUI
 DOTNET

 Algorithms used : DBN


REFERENCS
1) P. Bao, Xiaohu Ma, “Image adaptive watermarking using wavelet domain singular value
decomposition”, Circuits and Systems for Video Technology, IEEE, Transactions on, vol. 15, no. 1,
pp. 96–102, 2005.
2) T. Filler, J. Judas, and J. Fridrich, “Minimizing additive distortion in steganography using
syndrome-trellis codes,” Information Forensics and Security, IEEE Transactions on, vol. 6, no. 3, pp.
920–935, Sep. 2011.
3) Bin Li, Shunquan Tan, Ming Wang, and Jiwu Huang, “Investigation on cost assignment in spatial
image steganography,” Information Forensics and Security, IEEE Transactions on, vol. 9, no. 8, pp.
1264–1277, 2014.
4) L. Guo, J. Ni, and Y. Q. Shi, “Uniform embedding for efficient JPEG steganography,” Information
Forensics and Security, IEEE Transactions on, vol. 9, no. 5, pp. 814–825, May 2014.
5) V. Holub, J. Fridrich, and T. Denemark, “Universal distortion function for steganography in an
arbitrary domain,” EURASIP Journal on Information Security, vol. 2014, no. 1, pp. 1–13, 2014

You might also like