<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=undefined&type=result"></script>');
-->
</script>
Цель работы – разработка прототипа нейроÑетевой ÑиÑтемы компьютерного Ð·Ñ€ÐµÐ½Ð¸Ñ Ñ Ð¼ÐµÑ…Ð°Ð½Ð¸Ð·Ð¼Ð¾Ð¼ защиты от бÑкдор-атак. Применено Ñпециализированное программно-математичеÑкое обеÑпечение pycharm. Ð’ результате иÑÑÐ»ÐµÐ´Ð¾Ð²Ð°Ð½Ð¸Ñ Ð±Ñ‹Ð» проведен обзор ÑиÑтем компьютерного Ð·Ñ€ÐµÐ½Ð¸Ñ Ð¸ ÑущеÑтвующих методов атак на них, а также методов борьбы Ñ Ñтими атаками. Ð’ работе была предложена Ð½Ð¾Ð²Ð°Ñ Ð¼ÐµÑ‚Ð¾Ð´Ð¸ÐºÐ° защиты, оÑÐ½Ð¾Ð²Ð°Ð½Ð½Ð°Ñ Ð½Ð° иÑпользовании Ñ…Ñш функций и протокола TLS Ð´Ð»Ñ Ð·Ð°Ñ‰Ð¸Ñ‚Ñ‹ канала передачи данных, ÐºÐ¾Ñ‚Ð¾Ñ€Ð°Ñ Ð¿Ð¾ÐºÐ°Ð·Ð°Ð»Ð° Ñвою ÑффективноÑть в защите пользовательÑких данных от подмены. При разработке прототипа нейроÑетевой ÑиÑтемы были учтены Ñформированные Ñ‚Ñ€ÐµÐ±Ð¾Ð²Ð°Ð½Ð¸Ñ Ðº ÑиÑтеме и на их оÑнове Ñформирована архитектура ÑиÑтемы. Модель Ð²Ð½ÐµÐ´Ñ€ÐµÐ½Ð¸Ñ Ð±Ñкдоров в Ð¸Ð·Ð¾Ð±Ñ€Ð°Ð¶ÐµÐ½Ð¸Ñ Ð±Ñ‹Ð»Ð° разработана Ð´Ð»Ñ Ð´ÐµÐ¼Ð¾Ð½Ñтрации работы разработанного механизма выÑÐ²Ð»ÐµÐ½Ð¸Ñ Ð¸ ÑмÑÐ³Ñ‡ÐµÐ½Ð¸Ñ Ð±Ñкдоров. Механизм выÑÐ²Ð»ÐµÐ½Ð¸Ñ Ð¸ ÑмÑÐ³Ñ‡ÐµÐ½Ð¸Ñ Ð±Ñкдоров был разработан на оÑнове анализа изменений в точноÑти клаÑÑификации данных при внедрении бÑкдоров. Результаты работы алгоритма показали ÑффективноÑть предложенной методики защиты от бÑкдор-атак. Таким образом, результаты работы предÑтавлÑÑŽÑ‚ новизну в облаÑти защиты нейроÑетевых ÑиÑтем компьютерного Ð·Ñ€ÐµÐ½Ð¸Ñ Ð¾Ñ‚ бÑкдор-атак и могут быть иÑпользованы Ð´Ð»Ñ ÑƒÐ»ÑƒÑ‡ÑˆÐµÐ½Ð¸Ñ Ð±ÐµÐ·Ð¾Ð¿Ð°ÑноÑти подобных ÑиÑтем.
The object of research is neural network systems of computer vision. The purpose of the work is to develop a prototype of a neural network computer vision system with a mechanism to protect against backdoor attacks. Specialized software and mathematical software pycharm was used. As a result of the study, a review of computer vision systems and existing methods of attacks on them, as well as methods for combating these attacks, was carried out. The work proposed a new protection technique based on the use of hash functions and the TLS protocol to protect the data transmission channel, which has shown its effectiveness in protecting user data from spoofing. When developing a prototype of a neural network system, the formed requirements for the system were taken into account and, on their basis, the system architecture was formed. The image backdoor injection model was developed to demonstrate the operation of the developed mechanism for detecting and mitigating backdoors. The mechanism for detecting and mitigating backdoors was developed based on the analysis of changes in the accuracy of data classification when backdoors are introduced. The results of the algorithm showed the effectiveness of the proposed method of protection against backdoor attacks. Thus, the results of the work represent a novelty in the field of protecting neural network computer vision systems from backdoor attacks and can be used to improve the security of such systems.
бÑкдоÑ, ÑÑоÑнÑÐºÐ°Ñ Ð°Ñака, заÑажение даннÑÑ, компÑÑÑеÑное зÑение, data infection, ÐейÑоннÑе ÑеÑи, ÐнÑоÑмаÑиÑ, trojan attack, клаÑÑиÑикаÑÐ¸Ñ Ð¸Ð·Ð¾Ð±Ñажений, backdoor, computer vision, image classification
бÑкдоÑ, ÑÑоÑнÑÐºÐ°Ñ Ð°Ñака, заÑажение даннÑÑ, компÑÑÑеÑное зÑение, data infection, ÐейÑоннÑе ÑеÑи, ÐнÑоÑмаÑиÑ, trojan attack, клаÑÑиÑикаÑÐ¸Ñ Ð¸Ð·Ð¾Ð±Ñажений, backdoor, computer vision, image classification
citations This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |