Journal of Cybersecurity and Information Management

Secure protection of sensitive data and financial transactions is of the utmost importance in the dynamic world of online trade. In this study, we present a full-stack security architecture that uses five separate algorithms: ECF, Transaction Anomaly Detection, Adaptive Threat Intelligence, Behavioral Biometric Authentication, and Dynamic Encryption Protocol. By creating encryption keys on the fly while the user logs in, the DEP method lays a solid groundwork for safe data transfer. Behavioral biometric authentication (BBA) uses DEP output to verify users based on their distinct behavior, which is an extra layer of security. By combining both current and past threat information, the ATI algorithm is able to constantly adjust security protocols, providing a preventative shield against new dangers. TAD is an expert at detecting anomalies in online purchases, which helps keep financial transactions honest. When ECF and DEP work together, they filter email content, making communication more secure. Flowcharts help to illustrate the interactions between various algorithms, which helps to understand their operations in detail. Every algorithm's importance is brought to light by an ablation study, which shows how each one contributes and how they all work together to affect the overall security posture. The suggested security framework outperforms the state-of-the-art in terms of efficacy, adaptability, and usability, according to performance evaluations conducted using a number of metrics. These findings can help decision-makers build a strong security plan that is specific to the challenges of online shopping. To conclude, the suggested framework is an integrated and complementary strategy that will strengthen online trade in the face of several cyber dangers while simultaneously protecting the confidentiality, authenticity, and availability of all associated communications and transactions.

With the increased use of the Internet, unauthorized access has increased, allowing malicious users to hack networks and carry out malicious activities. One of the essential modern approaches in today's cybersecurity efforts is the limitation of access by suspect users. In this study, the approach toward real-time intrusion detection was to consider behavioral patterns of past users on the network. We classified the users as two categories: intervention and non-intervention, and employed the machine learning techniques Artificial Neural Networks [ANN], Support Vector Machines [SVM], and Decision Trees [DT]. The Decision Trees model was chosen as it had a mature capability concerning complex pattern recognition and an enhancement capability of the intrusion detection systems. The efficiency of these algorithms is examined via the key performance metrics: confusion matrix, F1-score, and Area Under the Curve [AUC]. Decision Tree, which came up as the best model for both the training and testing phases, produced an outstanding F1-score of 99.96% and AUC score of 99.93% in the testing phase. SVM and ANN gave good results; the F1 scores of SVM and ANN in the testing phase were 92.76% and 93.33%, while the AUC was 90.57% and 94.78%, respectively. This research will enlighten us on the influence of machine learning on the scope of intrusion detection, fostering more development efforts toward more responsive and dynamic intrusion detection systems. The comparative evaluation of these models will help in providing vital information for the further enhancement of cybersecurity strategies, ensuring better defenses against these ever-evolving cyber threats.

BD and AI are now transforming the banking and finance industry at a very fast pace, which is leading to change in the banking and finance institutions. This change is making them better, customer-oriented and financially rewarding organizations. Big data and AI have been useful in the banking and financial institutions to assess and manage the risks. Through the analysis of big amounts of unstructured data in real time, AI algorithms are capable of identifying risks. This makes it easy to put preventive measures in place to avert the risks. In addition, big data and AI have come a long way in solving the problem of fraud in banking and finance. This paper showed how big data and AI improve risk management, Cyber threat, and fraud in banking and finance by using data analysis and data pattern identification in real-time. That is why our work emphasizes the importance of implementing secure privacy and explaining the AI algorithm to eliminate ethical and Cyber security issues. Using analytical approaches, AI can identify the transactions with the help of comparison with the previous data and the behavioral characteristics related to the fraud. This approach to fraud prevention has been effective in reducing losses while at the same time improving the customer’s confidence in the company. On the other hand, there are disadvantages of big data and AI such as privacy, security, and ethical issues. Measures that can be used to safeguard customer information have to be employed in order to effectively safeguard the consumer data. Furthermore, transparency and accountability of the AI algorithms are crucial in order to avoid unfair decisions.