Filters








458,199 Hits in 3.7 sec

Detecting Simulated Attacks in Computer Networks Using Resilient Propagation Artificial Neural Networks

Mario A. Garcia, Tung Trinh
2015 POLIBITS Research Journal on Computer Science and Computer Engineering With Applications  
Intrusion detection systems using neural networks have been deemed a promising solution to detect such attacks.  ...  The Data Preprocessing module performs normalizing data function while the Neural Network processes and categorizes each connection to find out attacks.  ...  The approach is tested on eight neural network configurations and the results are compared with other approaches found in the literature. A.  ... 
doi:10.17562/pb-51-1 fatcat:6c3dmnumsbbirg4or6xi2ym63m

Neural Network Model for Detecting Network Scanning Attacks

Oleg Yuryevich Panischev, Artur Tagirovich Makridin, Alexey Sergeevich Katasev, Amir Muratovich Akhmetvaleev, Dina Vladimirovna Kataseva
2020 International journal of engineering research and technology  
It is proposed to use a trained neural network as a tool for detecting network scanning attacks.  ...  The Deductor modeling environment was used to build a neural network model.  ...  ACKNOWLEDGEMENTS The work is performed according to the Russian Government Program of Competitive Growth of Kazan Federal University.  ... 
doi:10.37624/ijert/13.11.2020.3596-3600 fatcat:qspkedyzv5eongb46k5olsqtmu

A neural network approach to photometric stereo inversion of real-world reflectance maps for extracting 3-D shapes of objects

K.V. Rajaram, G. Parthasarathy, M.A. Faruqi
1995 IEEE Transactions on Systems, Man and Cybernetics  
Presents a neural network approach to the problem of photometric stereo inversion of the reflectance maps of real-world objects for the purpose of estimating the 3-D attitudes of the surface patches of  ...  Using the surface normals estimated by the neural network, 3-D shapes of the objects have been reconstructed to a good approximation Index Terms: backpropagation feedforward neural nets image reconstruction  ...  Abstract: Presents a neural network approach to the problem of photometric stereo inversion of the reflectance maps of real-world objects for the purpose of estimating the 3-D attitudes of the surface  ... 
doi:10.1109/21.400507 fatcat:cqnzylaxnne4rkigix3mbvgykq

Siamese neural networks for continuous disease severity evaluation and change detection in medical imaging

Matthew D. Li, Ken Chang, Ben Bearce, Connie Y. Chang, Ambrose J. Huang, J. Peter Campbell, James M. Brown, Praveer Singh, Katharina V. Hoebel, Deniz Erdoğmuş, Stratis Ioannidis, William E. Palmer (+2 others)
2020 npj Digital Medicine  
To address these issues, we developed a convolutional Siamese neural network approach to evaluate disease severity at single time points and change between longitudinal patient visits on a continuous spectrum  ...  The Siamese neural network output for each image in comparison to a pool of normal reference images correlates with disease severity rank (ρ = 0.87 for ROP and ρ = 0.89 for osteoarthritis), both within  ...  This research was carried out in whole or in part at the Athinoula A.  ... 
doi:10.1038/s41746-020-0255-1 pmid:32258430 pmcid:PMC7099081 fatcat:b6vn2hm3qfaoxom2bbmwdchvl4

A NETWORK BASED INTRUSION DETECTION MODEL USING NEURAL NETWORK

Mohamed Ibrahim, Ismail Taha, Housam AI-Aloun
2003 International Conference on Aerospace Sciences and Aviation Technology  
This paper presents a neural network based implementation of an intrusion detection system to detect network based attacks.  ...  These selected features will be used an input features to train a designed neural network architecture to build a classifier that can recognize anomalies and known intrusions.  ...  -Neural network Approach: in this approach a neural network is used to be trained to learn the normal behavior and attack patterns, then significant deviations from normal behavior are flagged as attacks  ... 
doi:10.21608/asat.2013.24707 fatcat:ldu4snepxvfq7g4gvre6vkjxku

Input Data Analysis Using Neural Networks

Anil Yilmaz, Ihsan Sabuncuoglu
2000 Simulation (San Diego, Calif.)  
The performance of the proposed approach is measured with a number of test problems.  ...  In this paper, we investigate the feasibility of using neural networks in selecting appropriate probability distributions.  ...  The multiple neural network approach proposed in this paper and traditional goodness-of-fit tests (GFT) are not directly comparable, because the proposed approach is a meta model which selects a distribution  ... 
doi:10.1177/003754970007400301 fatcat:4ztui6wipffkljsw3foqsxhbcm

An enhanced artificial neural network for stock price predications

Jiaxin Ma, Silin Huang, S. H. Kwok
2016 International Journal of Business & Economic Development  
Artificial Neural Network (ANN) is a tool to solve this kind of problem and has received much attentions in the field of financial modeling in recent years.  ...  This paper proposes an enhanced ANN for predicting stock prices with a novel Max-Min normalization method as well as an iterative approach.  ...  The paper enhanced existing neural network models to increase the prediction accuracy. The major contribution of this paper is to advance the normalization method and the training approach.  ... 
doaj:4e244b1b359840a4bef72a17e0be3f63 fatcat:gn6vigacije2pfuzoclcjlsriu

Polychromatic neural networks

Francis T.S. Yu, Xiangyang Yang, Don A. Gregory
1992 Optics Communications  
We present a simple and general method to train a single neural network executable at different widths 1 , permitting instant and adaptive accuracy-efficiency trade-offs at runtime.  ...  Instead of training individual networks with different width configurations, we train a shared network with switchable batch normalization.  ...  SLIMMABLE NEURAL NETWORKS NAIVE TRAINING OR INCREMENTAL TRAINING To train slimmable neural networks, we begin with a naive approach, where we directly train a shared neural network with different width  ... 
doi:10.1016/0030-4018(92)90489-e fatcat:6yyv3zvp7jfk7mogt6oeah3why

Normality Testing for Vectors on Perceptron Layers

Youmna Shawki Karaki, Halina Kaubasa, Nick Ivanov
2020 European Journal of Engineering Research and Science  
Massive learning datasets prompt a researcher to exploit probability methods in an attempt to find optimal structure of a neural network.  ...  In this article, the normality of probability distribution of vectors on perceptron layers was examined by the Multivariate Normality Test.  ...  EXPERIMENT ON DATASETS NORMALITY In our experiment, a test was performed on the distribution of neurons in the neural network in order to verify the hypothesis of a multidimensional normal distribution  ... 
doi:10.24018/ejers.2020.5.9.2090 fatcat:yvyqxj7krfamtoeyerzfjra4ey

Slimmable Neural Networks [article]

Jiahui Yu, Linjie Yang, Ning Xu, Jianchao Yang, Thomas Huang
2018 arXiv   pre-print
We present a simple and general method to train a single neural network executable at different widths (number of channels in a layer), permitting instant and adaptive accuracy-efficiency trade-offs at  ...  Instead of training individual networks with different width configurations, we train a shared network with switchable batch normalization.  ...  SLIMMABLE NEURAL NETWORKS NAIVE TRAINING OR INCREMENTAL TRAINING To train slimmable neural networks, we begin with a naive approach, where we directly train a shared neural network with different width  ... 
arXiv:1812.08928v1 fatcat:wrojie66gzfwlfvizv5olagosy

IoT Malware Network Traffic Classification using Visual Representation and Deep Learning

Gueltoum Bendiab, Stavros Shiaeles, Abdulrahman Alruban, Nicholas Kolokotronis
2020 2020 6th IEEE Conference on Network Softwarization (NetSoft)  
To evaluate our proposed method performance, a dataset is constructed which consists of 1000 pcap files of normal and malware traffic that are collected from different network traffic sources.  ...  The experimental results of Residual Neural Network (ResNet50) are very promising, providing a 94.50% accuracy rate for detection of malware traffic.  ...  Furthermore, the two approaches were tested on small datasets (only 100 samples), which leads to restricting neural network training options.  ... 
doi:10.1109/netsoft48620.2020.9165381 dblp:conf/netsoft/BendiabSAK20 fatcat:qu5icb63e5gatgxncnrzaglvey

Neural network approach to real-time network intrusion detection and recognition

Pavel Kachurka, Vladimir Golovko
2011 Proceedings of the 6th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems  
We present recirculation neural network based approach which lets to detect previously unseen attack types in real-time mode and to further correct recognition of this types.  ...  In this paper we use recirculation neural networks as an anomaly detector as well as a misuse detector, ensemble of anomaly and misuse detectors, fusion of several detectors for correct detection and recognition  ...  In this paper the neural network based approach to anomaly and misuse detection on the basis of the analysis of the network traffic is described.  ... 
doi:10.1109/idaacs.2011.6072781 dblp:conf/idaacs/KachurkaG11 fatcat:ljqplikg5je3jmtkjefskr3wgi

Applying CMAC-based online learning to intrusion detection

J. Cannady
2000 Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium  
This paper presents a new approach to applying adaptive neural networks to intrusion detection that is capable of autonomously learning new attacks rapidly by a modified reinforcement learning method that  ...  Existing intrusion detection approaches require either manual coding of new attacks in expert systems or the complete retraining of a neural network to improve analysis or learn new attacks.  ...  Evaluate the ability of a CMAC neural network to recognize new patterns through generalization. 3. Test the ability of a CMAC neural network to autonomously learn new attacks on-line.  ... 
doi:10.1109/ijcnn.2000.861503 dblp:conf/ijcnn/Cannady00 fatcat:n2q5yh3ocrf73pz4kptrjeibd4

Neural network model for transient ischemic attacks diagnostics

V. Golovko, Henadzi Vaitsekhovich, E. Apanel, A. Mastykin
2012 Optical Memory and Neural Networks  
The proposed approach is based on integration of the NPCA neural network and multilayer perceptron. The dataset from clinic have been used for experiments performing.  ...  The main advantages of using neural network techniques are the ability to recognize 'novel" TIA attack instances, quickness and ability to assist the doctor in making decision.  ...  Output value of a neural network is the number in a range from 0 up to 1 which characterizes probability of diagnostics for corresponding class of TIA.  ... 
doi:10.3103/s1060992x12030095 fatcat:srxu4tok3vbuhdhsfrkm323fay

ANOMALY NETWORK INTRUSION DETECTION SYSTEM BASED ON DISTRIBUTED TIME-DELAY NEURAL NETWORK (DTDNN)

LAHEEB MOHAMMAD IBRAHIM
2010 Journal of Engineering Science and Technology  
This research aims to solve a hierarchical multi class problem in which the type of attack (DoS, U2R, R2L and Probe attack) detected by dynamic neural network.  ...  The results indicate that dynamic neural nets (Distributed Time-Delay Artificial Neural Network) can achieve a high detection rate, where the overall accuracy classification rate average is equal to 97.24%  ...  The inherent speed of neural networks is another benefit of this approach.  ... 
doaj:5535879e17e14ae09c75053a03e6c795 fatcat:dgqwthkqcnalvirusxpud6cddu
« Previous Showing results 1 — 15 out of 458,199 results