Beruflich Dokumente
Kultur Dokumente
net/publication/328531831
CITATIONS READS
2 72
2 authors, including:
Ajahar Ismailkhapathan
6 PUBLICATIONS 11 CITATIONS
SEE PROFILE
All content following this page was uploaded by Ajahar Ismailkhapathan on 26 October 2018.
implemented by using electronic components or is simulated in After studying the basic biological model of the neural network,
software on a digital computer. A neural network is a massively a mathematical model is envisaged to be designated. The
parallel distributed processor made up of simple processing mathematical model for such a neural network is given by:
units, which has a natural propensity for storing experimental ∑𝑛𝑖=1 𝑋𝑖𝑊𝑖 + Ɵ
knowledge and making it available for use. It resembles the Where Xi represents the signals arriving through various paths,
brain in two respects: Wi represents the weight corresponding to the various paths and
Ɵ is the bias. The above concept can be visualized by the
1. Knowledge is acquired by the network from its environment following diagram:
through a learning process.
2. Interneuron connection strengths, known as synaptic
weights, are used to store the acquired knowledge.
Neural networks, with their remarkable ability to derive
meaning from complicated or imprecise data, can be used to
extract patterns and detect trends that are too complex to be
noticed by either humans or other computer techniques. Other
advantages include:
2. Self-Organization: An ANN can create its own organization Figure 3. Mathematical model of a neural network
or representation of the information it receives during
learning time.
The above diagram exhibits the derived mathematical model of
3. Real Time Operation: ANN computations may be carried the neural network. It can be seen that various signals
out in parallel, and special hardware devices are being traverssing different paths have been assigned names X and
designed and manufactured which take advantage of this each path has been assigned a weight W. The signal traverssing
capability. a particular path gets multiplied by a corresponding weight W
and finally the overall summation of the signals multiplied by
The biological model of the neuron is shown in the the corresponding path weights reaches the neuron which reacts
figure. It consists of the cell body, axon hillock, action to it according to the bias Ɵ.
potential, synaptic terminal, axon of pre synaptic neuron and
dendrites. Signals from different parts of the body travel III. PROPOSED SCHEME
through different parts and reach the neuron where the neuron
processes it and produces an output. It should be noted though The crux of the entire proposed methodology can be explained
that the output of a neuron may also be fed to another neuron. using the block diagram of proposed method. The block
A collection of such neurons is called a neural network. The diagram of proposed method is explained under the following
neural network can perform simple to complex tasks depending different heading.
on the structure of the neural network. The proposed methodology can be explained according to the
following algorithm:
1. Initially the plain text is entered by the user and it is
displayed and stored. Subsequently, the plain text is
converted into its ASCII equivalent and the ASCII
equivalent of the plain text is displayed.
2. Next, the chaotic neural network is designed based on the
input adaptive weights, activation function and bias. The
critical aspect here is to design a neural network that
exhibits the property of chaos.
3. Once the chaotic neural network is designed, the ASCII
equivalent of the input is applied to the network to obtain
the cipher text. Subsequently the cipher text is displayed.
Figure 2. Biological model of neuron
VI. CONCLUSION [9] Wenwu Yu, Jinde Cao, ―Cryptography based on delayed
chaotic neural networks‖, Physics Letters A, Vol. 356, (4)
It can be concluded from the above mentioned results Elsevier, 333– 338, 2006.
that the proposed algorithm achieves a higher throughput [10] Jiyun Yang, Xiaofeng Liao, Wenwu Yu, Kwok-wo Wong,
compared to the standard data encryption algorithms. This has Jun Wei, ―Cryptanalysis of a cryptographic scheme based
a very important repercussion that the proposed algorithm can on delayed chaotic neural networks‖, Chaos, Solitons&
be treated as a light weight algorithm which can find its Fractals, Vol. 40, Issue.2, 821- 825, 2009.
applications not only on computational machines with [11] Jangid sheetal Kailash, Vaishnika Balmukund Patil, Neha
substantial resources but also on computational platforms with Vinay Patil, Ajahar Ismailkha Pathan,” Behavioural,
limited resources such as mobile computing. The Avalanche Emotional State Based Music Selection & Playlist
effect is comparable to standard algorithms. The Bit Generating Player”, International Journal Of Current
Independence Criteria clearly exhibits the fact that the bits in Engineering And Scientific Research, Vol-4(12), pp. 39-
the cipher text change independently of each other and satisfy 43, Dec 2017
the condition for chaos. It can be thus concluded that that the [12] Shweta B. Suryawanshi, Devesh D. Nawgaje, ―A triple-
proposed algorithm for data encryption using a chaotic neural key Chaotic neural network for cryptography in image
network holds good as an effective yet light weight encryption processing‖, International Journal of Engineering Sciences
variant. & Emerging Technologies, Vol. 2, Issue. 1, 46-50, 2012.
[13] Nitin Shukla, Abhinav Tiwari, ―An Empirical
REFERENCES Investigation of Using ANN Based N-State Sequential
Machine and Chaotic Neural Network in the Field of
[1] William Stallings, ―Cryptography and Network Security: Cryptography‖, Global Journal of Computer Science and
Principles and Practice‖, (5th Edition), Prentice Hall, 2010. Technology Neural & Artificial Intelligence, Vol. 12,
[2] T. P.Wasnik , Vishal S. Patil , Sushant A. Patinge , Sachin Issue.10,No. 1,17-26, 2012.
R. Dave , Gaurav J. Sayasikamal, ―Cryptography as an [14] Tariq A. fadil, Shahrul N. yaakob, Badlishah ahmad, abid
instrument to network security‖, International Journal of yahya, ―Encryption of mpeg-2 video signal based on
Application or Innovation in Engineering & Management chaotic neural network‖, Journal of Engineering and
(IJAIEM), Vol. 2, Issue 3, 72-80, 2013. Technology, Vol. 3, 35-42, 2012.
[3] Wolfgang Kinzel, IdoKanter, ―Neural Cryptography‖, [15] Navita Agarwal, Prachi Agarwal, ―Use of Artificial
Proceedings TH2002 Supplement, Vol. 4, 147 – 153, 2003. Neural Network in the Field of Security‖, MIT
[4] Einat Klein, Rachel Mislovaty, IdoKanter, Andreas Ruttor, International Journal of Computer Science & Information
Wolfgang Kinzel, ―Synchronization of neural networks Technology, Vol. 3, No. 1, 42–44, 2013.
by mutual learning and its application to cryptography‖, In [16] B. Geetha vani, E. V. Prasad, ―A Hybrid Model for Secure
proceeding of: Advances in Neural Information Processing Data Transfer in Audio Signals using HCNN and DD
Systems 17 ,Neural Information Processing Systems NIPS, DWT‖, (IJACSA) International Journal of Advanced
2004. Computer Science and Applications, Vol. 4, No.7, 202-
[5] N. Prabakaran, P. Vivekanandan, ―A New Security on 208, 2013.
Neural Cryptography with Queries‖, Int. J. of Advanced
Networking and Applications, Vol. 2, Issue. 1, 437-444,
2010.
[6] R. M. Jogdand, Sahana S. Bisalapur, ―Design of an
efficient neural key generation‖, International Journal of
Artificial Intelligence & Applications (IJAIA), Vol.2,
No.1, 60- 69, 2011.
[7] Ajahar Ismailkha Pathan, Amit Sinhal, “Encode Decode
Linux based Partitions to Hide and Explore File System”,
International Journal of Computer Applications, Vol.
75(12), pp. 40-45, Aug 2013.
[8] Pratap Singh, Harvir Singh, ―Cryptography in structure
adaptable digital neural networks", National monthly
refereed journal of research in science & technology,
Vol.1, Issue.12, 35-44, 2012.