79,980 Hits in 5.1 sec

Recognizing Functions in Binaries with Neural Networks

Eui Chul Richard Shin, Dawn Song, Reza Moazzezi
2015 USENIX Security Symposium  
Using a dataset from prior work, we show that recurrent neural networks can identify functions in binaries with greater accuracy and efficiency than the state-of-the-art machine-learning-based method.  ...  In this paper, we propose to apply artificial neural networks to solve important yet difficult problems in binary analysis.  ...  Acknowledgements We would like to thank Philipp Moritz for help with the initial implementation and experiments.  ... 
dblp:conf/uss/ShinSM15 fatcat:ekwjdkqvnbhv5hkrp32zzj2qqy


2001 International journal of pattern recognition and artificial intelligence  
Letting its hidden units be the respective perceptive neurons of the patterns, a three-layer forward neural network is constructed to recognize these patterns with minimum error probability in a noisy  ...  This paper presents a new neural network approach to real-time pattern recognition on a given set of binary (or bipolar) sample patterns.  ...  That is, the network recognizes the sample patterns with the minimum error probability in a noisy environment.  ... 
doi:10.1142/s0218001401001246 fatcat:ehkvbgq3bzdm3fbmavj3kvtbru

Problem Evolution: A new approach to problem solving systems [article]

Goren Gordon, Uri Einziger-Lowicz
2006 arXiv   pre-print
In this paper we implement this approach on pattern recognition neural networks to try and find the most complex pattern a given configuration can solve.  ...  The results demonstrate the power of the problem evolution approach in ranking different neural network configurations according to their pattern recognition abilities.  ...  In practice, we will use neural networks to fully recognize a binary image.  ... 
arXiv:cs/0609125v1 fatcat:4itve3nnane43e5tq76vzqr2gi

iCallee: Recovering Call Graphs for Binaries [article]

Wenyu Zhu, Zhiyao Feng, Zihan Zhang, Zhijian Ou, Min Yang, Chao Zhang
2021 arXiv   pre-print
In this paper, we propose a new solution iCallee based on the Siamese Neural Network, inspired by the advances in question-answering applications.  ...  The core challenge is recognizing targets of indirect calls (i.e., indirect callees). It becomes more challenging if target programs are in binary forms, due to information loss in binaries.  ...  Function Recovery. ByteWeight [76] shows that recurrent neural networks (RNNs) can identify functions in binaries precisely.  ... 
arXiv:2111.01415v2 fatcat:3dt3wngiyrbohk3gahv45pykzu


2013 American Journal of Applied Sciences  
In our study, we proposed an efficient Hindi Digit Recognition System drawn by the mouse and developed using Multilayer Perceptron Neural Network (MLP) with backpropagation.  ...  Handwritten Hindi digit recognition plays an important role in eastern Arab countries especially in the courtesy amounts of Arab bank checks, recognizing numbers in car plates, or in postal code for mail  ...  Different neural networks can be chosen to recognize the handwritten digits. Neural network with different number of layers and different neurons per layer have been trained and simulated.  ... 
doi:10.3844/ajassp.2013.938.951 fatcat:xxizb6rplbgtxbgo4yup7ala2q

Optimizing the Distribution of Memristance Values of Memristive Synapses for Reducing Power Consumption in Analog Memristor Crossbar-Based Neural Networks

2019 International Journal of Engineering and Advanced Technology  
A two-layer neural network is implemented using the memristor crossbar arrays, which can be used with analog synapse or binary synapse.  ...  In this paper, we compare the power consumption between an analog memristor crossbar-based a binary memristor crossbar-based neural network for realizing a two-layer neural network and propose an efficient  ...  Activation function circuits used in this neural network are the sigmoid functions realized by Op-amp circuits [14] .  ... 
doi:10.35940/ijeat.b3709.129219 fatcat:f2qokweebfgqlc55qxvu3ik2nu

Face Recognition Using Neural Networks

V. Ramya, G. Sivashankari
2011 International Journal of Electronics Signals and Systems  
The recognition is performed by Neural Network (NN) using Back Propagation Networks (BPN) and Radial Basis Function (RBF) networks.  ...  In feature Extraction, Distance between eyeballs and mouth end point will be calculated.  ...  Then the neural networks are tested with the remaining images. The BPN network accepts 2 unknown faces and it recognizes all the known faces.  ... 
doi:10.47893/ijess.2011.1015 fatcat:mlkm6hg2bfgybnqmo4zav2uz3e

Offline Character Recognition System Using Artificial Neural Network

Nisha Vasudeva, Hem Jyotsana Parashar, Singh Vijendra
2012 International Journal of Machine Learning and Computing  
A Neural network is designed to model the way in which the brain performs a particular task or function of interest. Each image character is comprised of 30×20 pixels.  ...  Features extracted from characters are directions of pixels with respect to their neighboring pixels. These inputs are given to a back propagation neural network with hidden layer and output layer.  ...  A back propagation feed-forward neural network is used to recognize the characters. After training the network with back-propagation learning algorithm, high recognition accuracy can be achieved.  ... 
doi:10.7763/ijmlc.2012.v2.165 fatcat:okcadow7djg3vhssmlgxqsyatq

Recognition of Text Image Using Multilayer Perceptron [article]

Singh Vijendra, Nisha Vasudeva, Hem Jyotsana Parashar
2016 arXiv   pre-print
A Neural network is designed to model the way in which the brain performs a particular task or function of interest: The neural network is simulated in software on a digital computer.  ...  the neural network of multiple layers.  ...  A back propagation feed-forward neural network is used to recognize the characters. After training the network with back-propagation learning algorithm, high recognition accuracy can be achieved.  ... 
arXiv:1612.00625v1 fatcat:2o5yapvncjexpaqitcw25edyrm

A Low-cost Artificial Neural Network Model for Raspberry Pi

S. N. Truong
2020 Zenodo  
In this paper, a ternary neural network with complementary binary arrays is proposed for representing the signed synaptic weights.  ...  In conventional neural networks, the signed synaptic weights of –1, 0, and 1 are represented by 8-bit integers.  ...  For a multilayer neural network, the conventional ternary neural network requires a memory of 398.2754KB, whereas the proposed ternary neural network with a complementary binary array representing the  ... 
doi:10.5281/zenodo.3748348 fatcat:yn7nf2qv4jfy3nged4kdrszklu


2013 Journal of Computer Science  
In this study, backpropagation network algorithm is combined with genetic algorithm to achieve both accuracy and training swiftness for recognizing alphabets.  ...  The accuracy in recognizing character differ by 10, 77%, with a success rate of 90, 77% for the optimized backpropagation and 80% accuracy for the standard backpropagation network.  ...  Sigmoid Binary Function This function is useful in neural network with backpropagation training model because it is easy to distinguish and reduce the capacity needed Fig. 3 Equation (1) : -x 1 g(x)  ... 
doi:10.3844/jcssp.2013.1435.1442 fatcat:do4raryerfcjrgx3vhvw2lxway

Recognition of Handwritten Digits using Convolutional Neural Network and Linear Binary Pattern

The proposed model includes Convolutional Neural Network (CNN), a deep learning approach with Linear Binary Pattern (LBP) used for feature extraction.  ...  The proposed system can recognize any handwritten digits in the document which has been converted into digital format.  ...  with bunch of activation filters in activation function. convolution layer.  ... 
doi:10.35940/ijitee.a5045.119119 fatcat:eajmmlfsufhx5iu27uycbdeyui

General-Purpose Computation with Neural Networks: A Survey of Complexity Theoretic Results

Jiří Šíma, Pekka Orponen
2003 Neural Computation  
The underlying results concerning the computational power and complexity issues of perceptron, radial basis function, winner-take-all, and spiking neural networks are briefly surveyed, with pointers to  ...  In our survey, we focus mainly on the digital computation whose inputs and outputs are binary in nature, although their values are quite often encoded as analog neuron states.  ...  Binary-State Networks. For integer weights, these models coincide with finite binary-state recurrent networks employing the Heaviside activation function defined in equation 2.3.  ... 
doi:10.1162/089976603322518731 pmid:14629867 fatcat:yuuurl36qjalpj5i3qag7ll32m

New Neural Networks for the Affinity Functions of Binary Images with Binary and Bipolar Components Determining

Valerii Dmitrienko, Serhii Leonov, Aleksandr Zakovorotniy
2021 Advances in Science, Technology and Engineering Systems  
One of the disadvantages of discrete neural networks is that binary neural networks perceive the income data only when it's coded in binary or bipolar way.  ...  proximity functions for discrete objects with binary coding of their components.  ...  New Neural Networks that Recognize Binary Images with Binary Components The generalized block diagram of the Hamming neural network in Figure 1 clearly shows that the three main layers of a neural network  ... 
doi:10.25046/aj060411 fatcat:br6qtsp46zcwliy3ktnaqt2vfi

High Accuracy Arabic Handwritten Characters Recognition Using Error Back Propagation Artificial Neural Networks

Assist. Prof., Assist. Prof.
2015 International Journal of Advanced Computer Science and Applications  
Neural Network (EBPANN).  ...  This manuscript considers a new architecture to handwritten characters recognition based on simulation of the behavior of one type of artificial neural network, called the Error Back Propagation Artificial  ...  Theoretically neural network with one hidden layer with a sufficient number of hidden cells is capable of approximating any continuous function.  ... 
doi:10.14569/ijacsa.2015.060221 fatcat:acpjg4mfznachbcrhdi7dabwt4
« Previous Showing results 1 — 15 out of 79,980 results