Digital Innovation Adoption: Architectural Recommendations and Security Solutions

Blockchain technology has a key role in electronic health record systems for storing, accessing and securing patients’ medical records. Patients’ medical information is being stored like personal bio, diagnosis, treatments, etc. This information is very sensitive and private, and it has remained a big challenge to access and secure patient medical records in a decentralized manner. Blockchain has become very important for its use in storing, accessing and managing patient medical records in a very secure and decentralized manner. In this paper, a systematic literature review has been done to review blockchain architecture for electronic health records systems to store, access and secure patient medical records. The main objective of this paper is to highlight the use of blockchain in accessing and securing patient medical records. Moreover, some blockchain-based electronic health records systems have been presented to secure the records. Lastly, some challenges and gaps in using blockchain-based medical health records systems have been presented.

The Internet of Things (IoT) has garnered many ideas to create new IoT products as well as enhance their existing products with the help of the internet. Tesla is an example of an IoT device from the automotive industry. The most prominent feature of the vehicle was the over-the-air (OTA) updates. A few vulnerabilities were found in Tesla despite being one of the most secure vehicles in the world. The first vulnerability was in the vehicle's key system, where radio signals from the key fob were intercepted in a relay attack. The next vulnerability was due to the Tesla app, where the hacker obtained the owner's login credentials. Besides, the infotainment system of the vehicle also was compromised and hacked using a web browser bug known as a JIT bug. Lastly, Tesla vehicles also had a vulnerability in their navigation system too. This was demonstrated by a group of researchers who staged a GPS spoof attack on Tesla model 3 while it was in Autopilot mode. Fake satellite coordinates were transmitted by the researchers, who were then received by the GPS receiver. This caused the vehicle to decelerate and made an emergency turn-off at a narrow pit stop. These vulnerabilities can be fixed by following safety measures to counter cyberattacks. More layers of security should be installed on the existing security system to ensure the vehicle does not get exploited easily by hackers.

Criminals are working day and night to get hold of the data. They are also getting more intelligent and are also using AI-powered threats to exploit vulnerabilities to perform an attack. Information security is at a higher risk, now more than ever. Due to the popularity of internet usage by users, the IT infrastructure is prone to security threats. The damage done by computer malware and viruses is known to cost billions of US dollars. Hence, this paper reviews the ways of integrating technology such as machine learning, neural networks, deep learning, etc. which can help to develop an intelligent system to protect and prevent the IT infrastructure from security threats. The authors proposed AIVA, a Machine learning (ML) based detection system which is able to classify a suspicious object as “safe” or “dangerous”. AIVA is composed of three core components: static analysis, machine learning, and malicious detection. 

The Internet of Things (IoT) is a mesh network of “electronic things” that are capable of acquiring data using embedded sensors and customized software or technologies, amalgamating and exchanging the information with other devices, as well as executing a customized action. This encompasses everything connected to the internet from the smallest devices such as coffee makers to sophisticated industrial control systems. As the IoT aggressively becomes interwoven in every aspect of our lives, cyber-security has become a necessity. This research aims to highlight the security vulnerabilities in IoT-based Home Automation, discuss the risks that end users can be faced with, as well as provide defense against the classified risks.

The Internet of Things (IoT) technology has been applied to our daily life infrastructure to make our lives easier and more comfortable. However, various variations in the IoT reference architecture represent that the developers need to be aware in order to implement the technology in a secure and accurate form. The knowledge of these reference architectures is important as they provide the guidelines for IoT developers and enterprises to develop high-quality IoT products. Requirements such as security, data process, and privacy issues must always be concerned. The reference architectures are used in the development of IoT products. This paper discusses and explores IoT-related field topics ranging from IoT reference architecture to policy to governance. Different kinds of variations in the reference architecture and the IoT governance policy are discussed to ensure the integrity and security of information transmitted across devices in the IoT ecosystem.

Ransomware is one of the most popular threats in the cyber world. There is an emerging technique for integrating artificial intelligence (AI), deep machine learning, and facial mapping for creating fake videos of people doing and saying something that they have not actually done. Deepfake ransomware is an attack where deepfake technology is being used in ransomware campaigns. Anyone can become the victim or target of this attack, however, this research paper focuses on the impact of deepfake ransomware on organisations. It covers potential risks that an organization might face due to deepfake ransomware attacks such as customer trust, organization reputation, and many other impacts. Besides that, this paper also discusses defence techniques that an organization could consider implementing in protecting the organization against deepfake ransomware attacks. Implementing the defence without awareness will not be effective, hence it is highlighted several times in this paper, that awareness is needed amongst the employees and employers to prevent the organisation from deepfake ransomware. Additionally, it also mentions possible risk management, business continuity, and disaster recovery plans that should be considered by the organization whilst handling the situation of deepfake ransomware attacks. 

Credit card fraud is a growing concern, and it poses a significant threat as individual information is being misused and causing a substantial monetary loss. Hence, the prevention of credit card fraud is crucial. Credit card fraud detection is used to differentiate the transactions, either as legitimate or fraudulent. Recently, different machine learning techniques have been implemented to detect credit card fraud. However, the main challenge with fraud detection is that the credit card data is highly skewed, with the fraudulent transactions as less as 1% of the total data. This study investigates the performance of the four supervised machine learning algorithms: logistic regression, support vector machine, decision tree, and random forest, along with different sampling techniques to better understand the fraud detection attributes and performance measures associated with it. This review is also concentrated on exploring different works where the model has a better value for all of the performance evaluation metrics: Recall, precision, F1-score, accuracy, MCC, AUC, and area under the precision-recall curve. This will detect credit card fraudulent transactions better and control credit card fraud.