Unified Cybersecurity Data Analytical Model for Smart Learning Operations

Unified Cybersecurity Data Analytical Model for Smart Learning Operations

Palanivel Kuppusamy, Suresh Joseph K.
DOI: 10.4018/978-1-6684-6092-4.ch006
OnDemand:
(Individual Chapters)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

In the fast-changing global environment, educational apps are widely used with hybrid and multi-cloud environments and intelligent devices. They offer various society services such as quality data for monitoring and prediction skills with protection and reliability. Smart learning systems pose a unique security risk because many people access and operate different techniques simultaneously over multiple networks. As a result, cybercrime has been brought about by the internet and the availability of intelligent devices. The security of online learning systems has received significant consideration. Because today's creative learning is open, distributed, and networked, ensuring that authorized users only have access to the appropriate data at the right time is a considerable challenge. The current security practices are outdated; hence, this chapter examines cyber-attacks on smart learning systems from their standard architecture and security requirements and proposes a cyber security model for educational operations from a multi/hybrid cloud-based learning environment.
Chapter Preview
Top

I. Introduction

The education system currently faces various difficulties, including poor quality, high dropout rates, low enthusiasm, health and nutritional needs for students from poorer households, a weak reading environment, and gender inequities (Government of Rwanda, 2020). The other challenge is improving access to education for vulnerable students, especially those with disabilities. To address these challenges, a transition is required to track the education coverage and access to understand education quality and equity across different dimensions. The present education system must be assessed and changed to keep up with modern business trends (Linda Darling-Hammond et al., 2020). To achieve this, the education sector needs data to respond to policy and planning questions and the changing reforms in the education system.

The next-generation digital learning ecosystem (Rob Abel, 2017), shown in Figure 1, can be built on a technological foundation that smoothly integrates established and new digital products. Digital devices and technologies can enable the development of smart and intelligent services in education. Educational sectors use smart technologies such as mobile, unified communications, remote access solutions, educational platforms, and tools in their environment. Smart technologies (Palanivel, 2020) include artificial intelligence (AI), blockchain, big data, cloud computing, edge computing, the Internet of Things (IoT), Machine Learning (ML), Deep Learning (DL), and robotic process automation (RPA), which fundamentally changes how education is conducted through the Internet and prompted the creation of a smart learning environment (SLE).

Figure 1.

Next-generation digital learning system

978-1-6684-6092-4.ch006.f01

SLE powers data-driven solutions in educational operations (García-Tudela, 2021). This data can be used to manage finances, oversee and enhance instruction, monitor teaching-learning activities, evaluate student learning outcomes, monitor progress, and contain educational materials. Data can highlight differences and allow decision-makers to design policies that ensure equity and resource allocations in the context of Sustainable Development Goals (SDG) (Unesco, 2017).

Educational institutions, including Higher Education Institutions (HEIs), research organizations, and training centers, require an integrated view across the organizations (Sonali 2019) to give strategies to regulate and handle the educational data. With supply chain data and analytics apps, this integrated view combines technical, academic, and operational processes. HEIs store a substantial amount of confidential information, including student identities and priceless intellectual property, which, if stolen, could cause serious harm that extends outside the institution's boundaries. The vast amount of private information kept by HEIs, including student identities and priceless intellectual property, could be seriously damaged if hacked. Topal (2022) states that HEIs are particularly vulnerable for the following reasons.

  • 1.

    Many HEIs still rely on outdated systems, which are attackable.

  • 2.

    HEIs, take pride in their lack of openness and transparency.

  • 3.

    Because HEIs are accessible online, attacks are aware of these shortcomings.

  • 4.

    Attackers can take advantage of educational institutions that are hopelessly out-of-date and under-resourced by utilizing cutting-edge techniques and technologies.

Complete Chapter List

Search this Book:
Reset