Zhengzhou Preschool Education College, Zhengzhou 450000, China.
Comput Intell Neurosci. 2022 Apr 28;2022:8548534. doi: 10.1155/2022/8548534. eCollection 2022.
Covid-19 pandemic has ushered in a new school and academic year for students in a distance learning regime. This new daily routine was unprecedented and undoubtedly unusual, especially for the younger ones. At this point and at these ages, the risk of cyber fraud is even greater. The transition from the physical environment to the Internet took place quickly without the appropriate time to control potential risks and the proper information and training of teachers and students. Some common threats that need to be addressed to protect learners and their data when using e-learning methods are malicious remote access, malware, phishing, cyber fraud, etc. Considering the above situation, this work presents an innovative cyber risk recommendation system for digital education management platforms. The system in question is a distributed two-stage algorithm based on game theory and machine learning, which is trained by the constant change in the choice of recommendations by users to maximize security. We examine the algorithm's ability to simulate a user system in which everyone independently selects a user recommendation, assesses the environment and the implications of this choice, and then concludes whether it will continue to have that recommendation fixed. The methodology with which we have represented the digital e-learning system has been done with an approach that directly corresponds with their general view as a cyber-physical-social system. We consider the digital school as an environment that brings limitations, leading us to a pretty demanding personalization problem. Users coexist in this environment, in which everyone acts voluntarily but influences and is influenced by the surrounding environment. Our results lead us to conclude that this algorithm responds in a fully effective, flexible, and efficient way to the needs of protection and risk assessment of e-learning education systems.
新冠疫情大流行使学生们进入了远程学习的新学年。这种新的日常生活是前所未有的，无疑是不寻常的，尤其是对年幼的学生来说。在这个时候和这个年龄段，网络诈骗的风险更大。从实体环境向互联网的过渡是迅速发生的，没有适当的时间来控制潜在的风险，也没有对教师和学生进行适当的信息和培训。在使用电子学习方法时，需要解决一些常见的威胁，以保护学习者及其数据，这些威胁包括恶意远程访问、恶意软件、网络钓鱼、网络欺诈等。考虑到上述情况，这项工作提出了一种创新的网络风险推荐系统，用于数字教育管理平台。所讨论的系统是一种基于博弈论和机器学习的分布式两阶段算法，通过用户推荐选择的不断变化进行训练，以最大限度地提高安全性。我们检验了该算法模拟用户系统的能力，在该系统中，每个人都独立选择用户推荐，评估环境及其选择的影响，然后决定是否继续使用该推荐。我们用来表示数字电子学习系统的方法是一种直接与作为网络物理社会系统的一般观点相对应的方法。我们将数字学校视为一个存在限制的环境，这导致了一个相当苛刻的个性化问题。用户在这个环境中共存，每个人都是自愿行动的，但会影响和受到周围环境的影响。我们的结果表明，该算法能够非常有效地、灵活地和高效地满足电子学习教育系统的保护和风险评估需求。
