This research aims to establish a secure system for key exchange by using post-quantum cryptography (PQC) schemes in the classic channel of quantum key distribution (QKD). Modern cryptography faces significant threats from quantum computers, which can solve classical problems rapidly. PQC schemes address critical security challenges in QKD, particularly in authentication and encryption, to ensure the reliable communication across quantum and classical channels. The other objective of this study is to balance security and communication speed among various PQC algorithms in different security levels, specifically CRYSTALS-Kyber, CRYSTALS-Dilithium, and Falcon, which are finalists in the National Institute of Standards and Technology (NIST) Post-Quantum Cryptography Standardization project. The quantum channel of QKD is simulated with Qiskit, which is a comprehensive and well-supported tool in the field of quantum computing. By providing a detailed analysis of the performance of these three algorithms with Rivest–Shamir–Adleman (RSA), the results will guide companies and organizations in selecting an optimal combination for their QKD systems to achieve a reliable balance between efficiency and security. Our findings demonstrate that the implemented PQC schemes effectively address security challenges posed by quantum computers, while keeping the the performance similar to RSA.

The rapid increase and adoption of Internet of Things (IoT) devices have introduced unprecedented conveniences into modern life. However, this growth has also ushered in a wave of cyberattacks targeting these often‐vulnerable systems. Smart cities, relying on interconnected sensors, are particularly susceptible to attacks due to the expanded entry points created by these devices. A security breach in such systems can compromise personal data and disrupt entire ecosystems. Traditional security measures are inadequate against the evolving sophistication of cyberattacks. The authors aim to address these challenges by leveraging honeypot data and machine learning to enhance IoT security. The research focuses on three objectives: identifying datasets from IoT‐targeted honeypots, evaluating machine learning algorithms for threat detection, and proposing comprehensive security solutions. Real‐world cyber‐attack datasets from diverse honeypots simulating IoT devices are analysed using various machine learning and neural network algorithms. Results demonstrate significant improvement in cyber‐attack detection and mitigation when integrating honeypot data into IoT security frameworks. The authors advance knowledge and provides practical insights for implementing robust security measures in diverse IoT applications, filling a crucial research gap.

In recent years, there has been a notable surge in both the complexity and volume of targeted cyber attacks, largely due to heightened vulnerabilities in widely adopted technologies. The Prediction and detection of early attacks are vital to mitigating potential risks from cyber attacks and network resilience. With the rapid increase of digital data and the increasing complexity of cyber attacks, big data has become a crucial tool for intrusion detection and forecasting. By leveraging the capabilities of unstructured big data, intrusion detection and forecasting systems can become more effective in detecting and preventing cyber attacks and anomalies. While some progress has been made on attack prediction, little attention has been given to forecasting cyber events based on time series and unstructured big data. In this research, we used the CSE-CIC-IDS2018 dataset, a comprehensive dataset containing several attacks on a realistic network. Then we used time-series forecasting techniques to construct time-series models with tuned parameters to assess the effectiveness of these techniques, which include Sequential Minimal Optimisation for regression (SMOreg), linear regression and Long Short-Term Memory (LSTM) to forecast the cyber events. We used machine learning algorithms such as Naive Bayes and random forest to evaluate the performance of the models. The best performance results of 90.4% were achieved with Support Vector Machine (SVM) and random forest. Additionally, Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) metrics were used to evaluate forecasted event performance. SMOreg’s forecasted events yielded the lowest MAE, while those from linear regression exhibited the lowest RMSE. This work is anticipated to contribute to effective cyber threat detection, aiming to reduce security breaches within critical infrastructure.

Online banking systems have become an integral part of our daily lives, offering access to financial services through Internet technologies and applications, however, as these systems grow in prevalence, they also introduce significant security and privacy challenges. These systems can be exposed to various cybersecurity threats that can result in data breaches, compromise of sensitive financial information, reputational damage, and significant operational disruptions. The existing model designed to ensure the security of consumers and service providers often fails to address the unique security and privacy challenges posed by banking environments. This paper proposes an integrated management framework based on threat and risk models, specifically designed for online banking systems. The framework incorporates a comprehensive risk management process and systematic assessment techniques while considering security features attributed to the banking environment, threat landscapes, and accessible information within the banking. During the threat identification and vulnerability analysis phases, potential attack scenarios and their possible impacts are evaluated using pre-defined procedures while considering the context. The assessment process quantifies cybersecurity risks, facilitating the appropriate mitigation strategies to address identified threats and risks. The framework’s applicability has been evaluated to determine its potential for effective real-world implementation in online banking systems. The evaluation addressed the security and privacy challenges of digital banking, and its ability to integrate with existing technologies and regulatory requirements.

According to the latest Verizon DBIR report, credential abuse, including password reuse and human factors in password creation, remains the leading attack vector. It was revealed that most users change their passwords only when they forget them, and 35% of respondents find mandatory password rotation policies inconvenient. These findings highlight the importance of combining technical solutions with user-focused education to strengthen password security. In this research, the “human factor in the creation of usernames and passwords” is considered a vulnerability, as identifying the patterns or rules used by users in password generation can significantly reduce the number of possible combinations that attackers need to try in order to gain access to personal data. The proposed method based on an LSTM model operates at a character level, detecting recurrent structures and generating generalized masks that reflect the most common components in password creation. Open datasets of 31,000 compromised passwords from real-world leaks were used to train the model and it achieved over 90% test accuracy without signs of overfitting. A new method of evaluating the individual password creation habits of users and automatically fetching context-rich keywords from a user’s public web and social media footprint via a keyword-extraction algorithm is developed, and this approach is incorporated into a web application that allows clients to locally fine-tune an LSTM model locally, run it through ONNX, and carry out all inference on-device, ensuring complete data confidentiality and adherence to privacy regulations.