A Study of Distinguisher Attack on AES-128 and AES-256 Block Ciphers through Model Based Classification Using Neural Network

2015 ◽  
Vol 710 ◽  
pp. 133-138
Author(s):  
K. Vetrivel ◽  
S.P. Shantharajah
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Block Cipher ◽  
Research Work ◽  
Random Permutation ◽  
Advanced Encryption Standard ◽  
Text Block ◽  
Cipher Text ◽  
Encryption Algorithms ◽  
Symmetric Block

Modern encryption algorithms will focus on transforming rendered text block into a non-rendered block of symbols. The objective is to make the cipher block more non-interpretable. Distinguisher attack algorithm is used to distinguish cipher text from random permutation and other related algorithms. Currently, a cipher has been design to concentrate on distinguisher attack. In this research work, we have attempted to distinguish the cipher blocks of AES-128 (Advanced Encryption Standard) and AES-256 symmetric block cipher algorithms using an artificial neural network based classifier.

scholarly journals Pioneer dataset and recognition of Handwritten Pashto characters using Convolution Neural Networks

2020 ◽  
pp. 002029402096482
Author(s):  
Sulaiman Khan ◽  
Abdul Hafeez ◽  
Hazrat Ali ◽  
Shah Nazir ◽  
Anwar Hussain
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Support Vector Machine ◽  
Research Work ◽  
Recognition Rate ◽  
Recognition Task ◽  
Convolution Neural Network ◽  
Medium Size ◽  
Support Vector ◽  
Artificial Neural

This paper presents an efficient OCR system for the recognition of offline Pashto isolated characters. The lack of an appropriate dataset makes it challenging to match against a reference and perform recognition. This research work addresses this problem by developing a medium-size database that comprises 4488 samples of handwritten Pashto character; that can be further used for experimental purposes. In the proposed OCR system the recognition task is performed using convolution neural network. The performance analysis of the proposed OCR system is validated by comparing its results with artificial neural network and support vector machine based on zoning feature extraction technique. The results of the proposed experiments shows an accuracy of 56% for the support vector machine, 78% for artificial neural network, and 80.7% for the proposed OCR system. The high recognition rate shows that the OCR system based on convolution neural network performs best among the used techniques.

Effective Implementation of Value Engineering Using Artificial Neural Network Aid of Optimization Techniques

2019 ◽  
Vol 27 (03) ◽  
pp. 1950022 ◽  
Author(s):  
M. Prem Swarup ◽  
A. Prabhu Kumar
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Research Work ◽  
Optimization Techniques ◽  
Value Engineering ◽  
Training Algorithms ◽  
Air Conditioner ◽  
Ann Model ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Value Engineering (VE) is a method for characterizing the developed requirements of a product, and it is concerned with the selection of less excessive conditions. VE can understand and improve the optimal outcome such as quantity, security, unwavering quality and convertibility of each managerial unit. It is an incredible solving tool that can diminish costs while preserving or improving performance and quality requirements. In this research work, VE is presented to calculate the heating cost and cooling cost of the air conditioner with the assistance of an Artificial Neural Network (ANN) with an optimization model. This ANN model effectively chooses the maximum number of sources obtainable and the source respective method with low functional cost and energy consumption. For improving the prediction accuracy of VE in the ANN model, we have incorporated some training algorithms and optimized the network hidden layer and hidden neuron by Opposition Genetic Algorithm (OGA). From the results, trained ANN with OGA predicts the output with 96.02% accuracy and also minimum errors compared with the existing GA process.

Prediction of Life of Compound Die Using Artificial Neural Network (ANN)

2014 ◽  
Vol 622-623 ◽  
pp. 664-671 ◽  
Author(s):  
Sachin Kashid ◽  
Shailendra Kumar
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Sheet Metal ◽  
Research Work ◽  
Fem Simulation ◽  
Fem Analysis ◽  
Ann Model ◽  
Sheet Metal Parts ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Prediction of life of compound die is an important activity usually carried out by highly experienced die designers in sheet metal industries. In this paper, research work involved in the prediction of life of compound die using artificial neural network (ANN) is presented. The parameters affecting life of compound die are investigated through FEM analysis and the critical simulation values are determined. Thereafter, an ANN model is developed using MATLAB. This ANN model is trained from FEM simulation results. The proposed ANN model is tested successfully on different compound dies designed for manufacturing sheet metal parts. A sample run of the proposed ANN model is also demonstrated in this paper.

scholarly journals On the semantic security of cellular automata based pseudo-random permutation using results from the Luby-Rackoff construction

2015 ◽  
Vol 15 (1) ◽  
pp. 21
Author(s):  
Kamel Mohammed Faraoun
Keyword(s):  
Cellular Automata ◽  
Block Cipher ◽  
Random Permutation ◽  
Block Ciphers ◽  
Random Permutations ◽  
Semantic Security ◽  
Transition Rules ◽  
Reversible Cellular Automata ◽  
Symmetric Block ◽  
Number Of Iterations

This paper proposes a semantically secure construction of pseudo-random permutations using second-order reversible cellular automata. We show that the proposed construction is equivalent to the Luby-Rackoff model if it is built using non-uniform transition rules, and we prove that the construction is strongly secure if an adequate number of iterations is performed. Moreover, a corresponding symmetric block cipher is constructed and analysed experimentally in comparison with popular ciphers. Obtained results approve robustness and efficacy of the construction, while achieved performances overcome those of some existing block ciphers.

scholarly journals Development of Effective Artificial Neural Network Model using Sequential Sensitivity Analysis and Randomized Training

2021 ◽  
Vol 10 (6) ◽  
pp. 12-20
Author(s):  
Akshay Daydar ◽  
Keyword(s):  
Neural Network ◽  
Sensitivity Analysis ◽  
Artificial Neural Network ◽  
Research Work ◽  
Large Data ◽  
Qualitative Reasoning ◽  
Machine Learning Algorithms ◽  
Finance Industry ◽  
Training Approach ◽  
Artificial Neural

As the machine learning algorithms evolve, there is a growing need of how to train the algorithm effectively for the large data with available resources in practically less time. The paper presents an idea of developing an effective model that focuses on the implementation of sequential sensitivity analysis and randomized training approach which can be one solution to this growing need. Many researchers focused on the implementation of sensitivity analysis to eliminate the insignificant features ands reduce the complexity in data selection. These sensitivity analysis methods relatively take a large time for validation through modeling and hence found impractical for large data. On the other hand, the randomized training approach was found to be the most popular approach for training the data but there is a very brief explanation available in research articles on how this training method is meaningful in getting higher accuracy. The current work focuses on the use of sequential sensitivity analysis and randomized training in an artificial neural network (ANN) for high dimensionality thermal power plant data. The sequential sensitivity analysis (SSA) technique includes the use of correlation analysis (CA), Analysis of variance (ANOVA), Akaike information criterion (AIC) in a sequential manner to reduce the validation time for all possible feature combinations. Only selected combinations are then tested against different training methods such as downward extrapolation, upward extrapolation, interpolation and randomized training in ANN. The paper also focuses on suggesting the significance of training with randomized training with comparison-based qualitative reasoning. The statistical parameters, mean square error (RMSE), Mean absolute relative difference (MARD) and R Square (R^2)were accessed for validation purposes. The research work mainly useful in the field of Ecommerce, Finance, industry and in facilities where large data is generated.

Breaching Security of Full Round Tiny Encryption Algorithm

2018 ◽  
Vol 12 (1) ◽  
pp. 89-98
Author(s):  
Puneet Kumar Kaushal ◽  
Rajeev Sobti
Keyword(s):  
Block Cipher ◽  
Binary Sequence ◽  
Random Permutation ◽  
Encryption Algorithm ◽  
Hardware Cost ◽  
Cipher Text ◽  
Known Plaintext Attack

Tiny encryption algorithm is a 64-bit block cipher designed by Wheeler and Needham in 1994 and attracted much of its attention due to its capability of reducing the hardware cost. In this paper, we introduced coincidence count attack at bit level, a kind of known-plaintext attack and evaluated the resistance of TEA to withstand with it. We also examined confrontation of full round TEA against bit sum attack. Furthermore, we introduced a modest algorithm based on coincidence count and bit sum concept that makes it easy to find relevant plaintext corresponding to an arbitrary cipher text with a probability of 0.93. We also presented how cipher text originated from tiny encryption algorithm can be distinguished from a random permutation of binary sequence.

Determination of Isosteric Heat and Entropy of Sorption of Air Dried Sheet Rubber Using Artificial Neural Network Approach

2014 ◽  
Vol 541-542 ◽  
pp. 374-379 ◽  
Author(s):  
Kiattisak Suntaro ◽  
Supawan Tirawanichakul ◽  
Yutthana Tirawanichakul
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Moisture Content ◽  
Water Activity ◽  
Research Work ◽  
Isosteric Heat ◽  
Neural Network Approach ◽  
Heat Of Sorption ◽  
Artificial Neural

Equilibrium moisture contents (EMC) of air dried sheet (ADS) rubber were determined by commonly gravimetric-static method with saturated salt solution among surrounding temperatures of 40-70°C correlated to water activity (aw) ranges between 0.10 and 0.9. The experimental results was analyzed by 5 commonly EMC model. The results showed that equilibrium moisture content of ADS rubber decreased with increase of surrounding temperature at constant water activity and the simulated data using Chung-Pfost model has a good relation to experimental data with R2, RMSE and χ2 equal 0.9565, 0.0235 and 0.0006, respectively. However some physical property of ADS rubber sample affects to evaluate EMC modeling. Due to avoid this effect, thus the aim of this research work was to determine EMC value by using Artificial neural network (ANN) method and also evaluate the isosteric heat of sorption by following the Clausius-Clapeyron equation. The results showed that simulated results using ANN approach has relatively high accuracy compared to common EMC model. Finally determination of isosteric heat of sorption and entropy of sorption of ADS rubber were carried on. The results stated that the enthalpy and entropy of heat sorption was power function and polynomial function of moisture content respectively. These two parameters of ADS rubber can be used for prediction suitable storage condition and drying condition for ADS rubber drying in the near future work.

scholarly journals Artificial Neural Network Modeling and Sensitivity Analysis of Performance and Emissions in a Compression Ignition Engine Using Biodiesel Fuel

Energies ◽  
2018 ◽  
Vol 11 (9) ◽  
pp. 2410 ◽  
Author(s):  
Farzad Jaliliantabar ◽  
Barat Ghobadian ◽  
Gholamhassan Najafi ◽  
Talal Yusaf
Keyword(s):  
Neural Network ◽  
Sensitivity Analysis ◽  
Artificial Neural Network ◽  
Research Work ◽  
Neural Network Modeling ◽  
Biodiesel Fuel ◽  
Compression Ignition ◽  
Compression Ignition Engine ◽  
Performance And Emissions ◽  
Artificial Neural

In the present research work, a neural network model has been developed to predict the exhaust emissions and performance of a compression ignition engine. The significance and novelty of the work, with respect to existing literature, is the application of sensitivity analysis and an artificial neural network (ANN) simultaneously in order to predict the engine parameters. The inputs of the model were engine load (0, 25, 50, 75 and 100%), engine speed (1700, 2100, 2500 and 2900 rpm) and the percent of biodiesel fuel derived from waste cooking oil in diesel fuel (B0, B5, B10, B15 and B20). The relationship between the input parameters and engine cylinder performance and emissions can be determined by the network. The global sensitivity analysis results show that all the investigated factors are effective on the created model and cannot be ignored. In addition, it is found that the most emissions decreased while using biodiesel fuel in the compression ignition engine.

Prediction of Life of Die Block Using Artificial Neural Network

2014 ◽  
Vol 592-594 ◽  
pp. 689-693 ◽  
Author(s):  
Sachin Kashid ◽  
Shailendra Kumar
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Research Work ◽  
Fem Simulation ◽  
Fem Analysis ◽  
Die Design ◽  
Ann Model ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Important Activity

Prediction of life of die block is an important activity of die design usually carried out by highly experienced die designers in sheet metal industries. In this paper, research work involved in the prediction of life of die block of compound die using artificial neural network (ANN) is presented. The parameters affecting life of die block are investigated through Finite Element Method (FEM) analysis and the critical simulation values are determined. Thereafter, an ANN model is developed using MATLAB. This ANN model is trained from FEM simulation results. The proposed ANN model is tested successfully on different die block. A sample run of the proposed ANN model is also demonstrated in this paper.

scholarly journals Predicting the Land Value using Regression Techniques and Artificial Neural Network

2019 ◽  
Vol 9 (1S3) ◽  
pp. 431-436
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Tamil Nadu ◽  
Research Work ◽  
Land Value ◽  
Regression Techniques ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
The Cost ◽  
Cost Of Construction

Land value can be an important factor which influences the cost of construction on working in the project. The land has socio-economic and environmental values and the confronted problems on land involves the increasing costs for developing the land such as built up, agricultural, residential, commercial and industrial areas. Hence this paper concentrates on prediction of land value by considering some important factors that affects it. The study area has been selected under Tirupur district, being a developing one in Tamil Nadu. The eleven areas in four different taluks under Tirupur district were chosen for research work. The average values of monthly variation are taken for the chosen factor for the years from 2001 to 2017. Using regression analysis and artificial neural network, the prediction has been done for the future land value. The performance of both the model executed good and fit for forecasting results. Though both the model showed better results, Artificial Neural Network (ANN) showed accuracy than regression method.

Sign in / Sign up

Export Citation Format

Share Document