Network Traffic Anomaly Detection via Deep Learning

Network intrusion detection is a key pillar towards the sustainability and normal operation of information systems. Complex threat patterns and malicious actors are able to cause severe damages to cyber-systems. In this work, we propose novel Deep Learning formulations for detecting threats and alerts on network logs that were acquired by pfSense, an open-source software that acts as firewall on FreeBSD operating system. pfSense integrates several powerful security services such as firewall, URL filtering, and virtual private networking among others. The main goal of this study is to analyse the logs that were acquired by a local installation of pfSense software, in order to provide a powerful and efficient solution that controls traffic flow based on patterns that are automatically learnt via the proposed, challenging DL architectures. For this purpose, we exploit the Convolutional Neural Networks (CNNs), and the Long Short Term Memory Networks (LSTMs) in order to construct robust multi-class classifiers, able to assign each new network log instance that reaches our system into its corresponding category. The performance of our scheme is evaluated by conducting several quantitative experiments, and by comparing to state-of-the-art formulations.

System for Filtering Unwanted Applications of Internet Resources

Currently, the role of the Internet in the life of society is growing, and the state’s view of it is changing. Increasingly, the content posted on the Web goes beyond the laws of individual countries, their social norms, and the political lines of the authorities. Besides, Internet has a significant impact on intellectual property and telecommunications, jeopardizing the economic interests of many industries. These trends have contributed to the need to filter some types of content, and have caused disputes about the permissible limits of state intervention in the functioning of the network. Content filtering systems and methods were analyzed, and their applicability for each of the information leakage channels was determined: blocking by IP address, blocking by DNS record, blocking by URL, filtering by text content, filtering by extensions and file types, filtering search results. The project of a software package for filtering Internet traffic in the C# programming language was developed and its functionality was described. As a result of the experiments carried out by the filtering system, the following results were obtained: the correctness of filtering by DNS record, the correctness of filtering by URL were successfully checked, reports on identified blocked sites in the filtering log were generated. Thus, the successful conduct of experiments allows us to assert that the software package of content filtering of Internet traffic performs the tasks assigned to it.