Volume 5 Issue 1: June 2026

This study provides a comprehensive analysis of cognitive password systems as a secure and user-friendly alternative to traditional authentication mechanisms. Cognitive passwords leverage human memory, behavior, and perception to enhance usability while mitigating common security challenges such as poor memorability, password reuse, and susceptibility to attacks. The study systematically reviews various models, including graphical passwords, cognitive biometrics, and cognitive one-time passwords (OTPs), highlighting their strengths and limitations. To ensure a transparent and rigorous review, we employed a structured methodology comprising a multi-database literature search, clearly defined inclusion and exclusion criteria, and a thematic synthesis of the collected studies. Our findings indicate that cognitive password systems offer significant improvements in user experience and security but face critical challenges, including accessibility for individuals with cognitive or physical impairments, privacy concerns, vulnerability to social engineering, and scalability limitations. Furthermore, artificial intelligence (AI) emerges as a key enabler for enhancing personalization, adaptive authentication, and real-time security risk assessment. The study underscores the necessity of integrating AI thoughtfully to maximize the benefits of cognitive passwords. Overall, this research demonstrates the transformative potential of cognitive password systems in cybersecurity, emphasizing that addressing usability, privacy, and scalability challenges is essential for their practical adoption. The findings provide actionable insights for system designers, policymakers, and researchers aiming to advance secure and user-centered authentication frameworks.

• View PDF

Phishing attacks pose significant risks in the digital landscape, resulting in financial losses and sensitive information breaches. Traditional detection methods often struggle to keep pace with evolving threats, compromising their effectiveness. This study addresses these limitations by developing a robust detection system using a hybrid machine learning approach. We combine random forest, gradient boosting, and logistic regression algorithms to enhance phishing detection accuracy. A labeled dataset of URLs from Kaggle is utilized, with robust feature engineering extracting key attributes for model training. Following the CRISP-DM framework and leveraging Object-Oriented Programming principles, we develop a model that achieves strong performance metrics. The model's accuracy stands at 84%, with precision, recall, and F1-score values of 85%, 86%, and 84%, respectively. Notably, the model demonstrates excellent ability to differentiate between phishing and legitimate URLs, with an ROC AUC score of 91%. These results confirm the model's potential as a reliable phishing detection tool, capable of identifying phishing URLs effectively while minimizing false positives. Our research contributes to the development of more effective phishing detection strategies, ultimately safeguarding users and organizations from economic and reputational harm. By leveraging machine learning, we can develop more robust cybersecurity systems. Our proposed model can be seamlessly integrated into existing security frameworks to improve the detection of phishing threats.

• View PDF

Wireless networks generate large volumes of heterogeneous data from network elements, user equipment, and management systems, posing significant challenges for effective network monitoring, fault management, and resource optimization. Traditional rule-based or data-driven approaches often lack unified knowledge representation and reasoning capability, limiting their scalability and interpretability. To address these challenges, this paper proposes a knowledge-graph-based framework for wireless network knowledge construction, management, and application. The proposed framework integrates multi-source network data through ontology-driven modeling and rule-based semantic mapping, enabling structured representation of network entities, events, and their relationships. An event-driven incremental update mechanism is introduced to efficiently maintain the knowledge graph in dynamic network environments without full reconstruction. Furthermore, a lightweight reasoning mechanism is employed to infer implicit network states and support intelligent network management decisions. The framework is designed to balance expressiveness and computational efficiency, making it suitable for large-scale wireless networks. To quantitatively evaluate the effectiveness of the proposed approach, extensive experiments are conducted under different network scales. The experimental results demonstrate that the proposed framework consistently outperforms traditional rule-based methods in terms of fault localization accuracy and resource utilization efficiency, while exhibiting lower query latency and better scalability as the network size increases. The results indicate that the proposed knowledge-graph-based framework provides an effective and scalable solution for intelligent wireless network management, with potential applicability to fault detection, resource optimization, and network security analysis.

• View PDF

Star-connected computer networks are explored using the example of terahertz modeling. Existence conditions for the complete synchronization between constituent lasers are found numerically. Numerical simulations were conducted using the Matrix Laboratory (MATLAB) software to solve Delay Differential Equations. Extensive numerical simulations with different initial states confirm that high-quality, near-perfect complete synchronization between terahertz lasers occurs. As in the real world, parameters can differ; we simulated the star-connected computer network model with parameter mismatches of 3–5%. Still, we have obtained close to 100% of correlation between the dynamics of terahertz lasers. Synchronization is important in chaos-based communication. It is underlined that chaos-based communication security between computer networks can offer an additional layer of security to the traditional cryptography based on the Rivest, Shamir, and Adleman (RSA) algorithm. This algorithm uses the mathematical challenge of factoring very large prime numbers. The extra layer of security is of immense importance in light of the exponential increase in central processing units (CPUs) in computers. This is especially true in light of the quantum processing unit (QPU), which is the core processor of a quantum computer, using qubits in superposition and entanglement to perform complex, parallel calculations far beyond classical CPUs. Unlike traditional binary CPUs, QPUs excel at optimization, cryptography, and artificial intelligence tasks. 

• View PDF