No abstract

The object of research of this work is the methods of deep learning for source code vulnerability detection. One of the most problematic areas is the use of only one approach in the code analysis process: the approach based on the AST (abstract syntax tree) or the approach based on the program dependence graph (PDG). In this paper, a comparative analysis of two approaches for source code vulnerability detection was conducted: approaches based on AST and approaches based on the PDG. In this paper, various topologies of neural networks were analyzed. They are used in approaches based on the AST and PDG. As the result of the comparison, the advantages and disadvantages of each approach were determined, and the results were summarized in the corresponding comparison tables. As a result of the analysis, it was determined that the use of BLSTM (Bidirectional Long Short Term Memory) and BGRU (Bidirectional Gated Linear Unit) gives the best result in terms of problems of source code vulnerability detection. As the analysis showed, the most effective approach for source code vulnerability detection systems is a method that uses an intermediate representation of the code, which allows getting a language-independent tool. Also, in this work, our own algorithm for the source code analysis system is proposed, which is able to perform the following operations: predict the source code vulnerability, classify the source code vulnerability, and generate a corresponding patch for the found vulnerability. A detailed analysis of the proposed system’s unresolved issues is provided, which is planned to investigate in future researches. The proposed system could help speed up the software development process as well as reduce the number of software code vulnerabilities. Software developers, as well as specialists in the field of cybersecurity, can be stakeholders of the proposed system.

The current state of energy requires the development of new efficient approaches to coordinated management of the generation, conversion, accumulation and consumption of electrical energy in power systems of different levels, including for power systems built on the basis of the SmartGrid concept. The integration of electrical devices into a single system with the provision of a given quality of electric power consumption is achieved by using converter devices that allow the generators and consumers of energy dissimilar in the physical principle to unite in one network on the basis of the context. This system can manage large amounts of energy related data and have to be able to react in correct way when conditions real-time changes. The main goals are the construction of a context-dependent power management system that performs tasks related to forecasting and intelligent response to the actions of all electrical installations combined with converters into a single information environment for the purpose of rational energy use, operational management of normal and emergency modes of SmartGrid operation with regard to requirements for user comfort. The control system should be able to rationally manages energy, efficiently control normal and emergency conditions and to take into account the user comfort. Context-aware energy management system as a complex information processing system integrates such organization levels as: Renewable sources of energy; Power converters; Electrical devices; Digital sensors; User tasks.

No abstract

No abstract