articles

Currently, a new type of information security threat is spreading – hidden mining, which uses the computing resources of users through browsers. Malicious software based on WebAssembly files unauthorizedly uses the computing resources of users of computer systems. The existing methods for detecting “hidden miners” in the browser environment are based on: dynamic analysis algorithms, however, they have a number of limitations, for example, it is required that malicious software for hidden mining work for a certain period of time, they are characterized by a large number of false positives; algorithms of browser extensions that use blacklists to prevent unauthorized access to the user’s browser environment, however, attackers often change their domain names, etc. The relevance of using special protection tools against browser-based cryptominers is beyond doubt. The purpose of this study is to increase the level of security of the browser environment of users of computer systems. Achieving this goal is possible by solving the main task - the timely automated detection of “hidden miners” in the browser environment and the prevention of unauthorized mining. The article describes software that does not depend on the browser or operating system used, is resistant to attempts to circumvent protection by intruders, will allow users to reliably recognize “hidden miners”, and increase the level of information security of a computer system. The software is based on classification algorithms implemented on the basis of a convolutional neural network. The results of the study and experimental data showed that as a result of testing the software, the recognition accuracy of “hidden miners” in the browser environment is 91.37%.