Article named “Deep Learning Method for Denial of Service Attack Detection Based on Restricted Boltzmann Machine” of Head of department of the Institute of Information Technology of ANAS, PhD on technical sciences, associate professor Yadigar Imamverdiyev and leading scientific worker, PhD in technical sciences Fargana Abdullayeva was published in the Big Data journal.

The article considers the detection of DoS attacks in the network with Gaussian -Bernoulli Restricted  Boltzmann Machine (RBM), one of the deeper learning technology models. Seven layers were added between the apparent and hidden layers of the RBM for increasing  the accuracy of the DoS attack detection. High results were achieved in detecting DoS attacks by optimizing the hyper parameters of the proposed deep RBM model. In the present study, the form of the RBM that allows the application of continuous data was used and the probability distribution of the visible layer was replaced by the distribution of Gauss. Comparative analysis was conducted with deeper learning methods such as Bernoulli-Bernoulli RBM, Gauss-Bernoulli RBM, Deep Belief Network to assess the detection accuracy of DoS attacks on different metrics. Methods of detection of accuracy were checked on the NSL-KDD database. The proposed multifaceted deep Gaussian-Bernoulli type RBM showed higher results.

The journal is indexed in scientific bases such as MEDLINE, PubMed, PubMed Central, Science Citation Index Expanded, Journal Citation Reports / Science Edition, Scopus, and its impact factor is 1,239.

It should be noted that the article was published within the framework of grant project ‘’Development of methods and algorithms for providing information security in Big  data environment’’ (Grant No. EIF-KETPL-2-2015-1(25)-56/05/1) supported by the Science Development Fund under the President of the Republic of Azerbaijan and their application "

© All rights reserved. Citing to www.ict.az is necessary upon using news