Vol 51, No 1 (2017)

Nowadays, Denial of Service (DoS) attacks have become a major security threat to networks and the Internet. Therefore, even a naive hacker can launch a large-scale DoS attack to the victim from providing Internet services. This article deals with the evaluation of the Snort IDS in terms of packet processing performance and detection. This work describes the aspect involved in building campus network security system and then evaluates the campus network security risks and threats, mainly analyses the attacks DoS and DDoS, and puts forward new approach for Snort campus network security solutions. The objective is to analyze the functional advantages of the solution, deployment and configuration of the open source based on Snort intrusion detection system. The evaluation metrics are defined using Snort namely comparison between basic rules with new ones, available bandwidth, CPU loading and memory usage.

Graphic vertex-coloring has long been a classical problem for combinatorial optimization in the field of science and technology. No algorithm can give an optimal solution for graphic vertex-coloring in polynomial time so far, though it plays an important role in the field of mathematical science and technology. Hence the problem has always been a non-deterministic polynomial (NP) complete problem. The current computer parallel technology based on compute unified device architecture (CUDA) is a hot spot in the relevant field. This study put forward a method integrating parallel genetic algorithm and CUDA to solve the problem of graphic vertex-coloring. First, color sequences were coded and parallel genetic operators were designed, which was beneficial to the improvement of algorithm efficacy. Then parallelization reformation was performed on the above integrated algorithm using CUDA. Experimental results demonstrated that, the newly developed algorithm improved the calculation efficiency and reduced the computation time compared to traditional algorithms based on central processing unit (CPU). Thus plenty of cases can be effectively solved if the minimum coloring number of a known graphics is found.

Object classification is a common problem in artificial intelligence and now it is usually approached by deep learning. In the paper the artificial neural network (ANN) architecture is considered. According to described ANN architecture, the ANN models are trained and tested on a relatively small Color-FERET facial image database under different conditions. The best fine-tuned ANN model provides 94% face recognition accuracy on Color-FERET frontal images and 98% face recognition accuracy within 3 attempts. However, for improving recognition system accuracy large data sets are still necessary preferably consisting of millions of images.

In modern computer networks, loading and bandwidth of communication links are optimized for providing high-quality service of network traffic, new services and technologies. As a rule, for this task the protocols of dynamic routing based on Dijkstra’s algorithm are used. Protocols of multipath routing for ensuring reliability and accuracy of the provided information allow to divide critical traffic and to execute load balancing along several routes at the same time. The purpose of the work is development and research of the improved multipath adaptive routing model in computer networks with load balancing. In this work, we focused on indicator of jitter optimization between the paved paths and a deviation value of reserve routes from an optimal route. Comparison and estimation of the offered algorithm with some existing approaches, and also modeling and analysis on various topologies of computer networks have been carried out.