Abstract
Introduction: computerization of the vital activity system of modern society is gaining more and more large-scale boundaries every day. In this regard, the risk of loss and theft of confidential information in various ways, including through various attacks, also increases. Purpose: the aim of the study is to develop an optimal method for detecting attacks, using the example of SQL-Injection attacks, based on a given algorithm of artificial intelligence. Methods: a training system for artificial intelligence based on a given algorithm of artificial intelligence is proposed Results: as a result of the work carried out, a training system for artificial neural networks was proposed to detect signs of computer attacks based on the SQL-Injection programming language on information and communication systems in real time based on the logical regression method. This implementation of detecting SQL-Injection attacks can be implemented in the server part of a database of any level, since to protect against this type of attacks, it is necessary to carefully filter the input parameters whose values will be used to build an SQL query and, if an attack is detected, block or redirect all requests to a pre-prepared fake database, which will increase the probability of detecting computer attacks. Practical relevance: based on the analysis of scenarios of an intruder with user privileges on a local node, one of the possible implementations of detecting computer attacks of the type SQL injection by the method of logistic regression is considered. To do this, training data is generated and an attack is detected by a trained model. Discussion: the implementation of this program will allow for adaptive protection by analyzing received requests to the server.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.