With the increasing use of web applications, challenges in the field of cybersecurity are becoming more complex. This paper explores the application of fine-tuned large language models (LLMs) for the automatic generation of synthetic attacks, including XSS (Cross-Site Scripting), SQL Injections, and Command Injections. A web application has been developed that allows penetration testers to quickly generate high-quality payloads without the need for in-depth knowledge of artificial intelligence. The fine-tuned language model demonstrates the capability to produce synthetic payloads that closely resemble real-world attacks. This approach not only improves the model’s precision and dependability but also serves as a practical resource for cybersecurity professionals to enhance the security of web applications. The methodology and structured implementation underscore the importance and potential of advanced language models in cybersecurity, illustrating their effectiveness in generating high-quality synthetic data for penetration testing purposes. The research results demonstrate that this approach enables the identification of vulnerabilities that traditional methods may not uncover, providing deeper insights into potential threats and enhancing overall security measures. The performance evaluation of the model indicated satisfactory results, while further hyperparameter optimization could improve accuracy and generalization capabilities. This research represents a significant step forward in improving web application security and opens new opportunities for the use of LLMs in security testing, thereby contributing to the development of more effective cybersecurity strategies.

The paper presents the dynamic model of maintenance costs of the power transformer functional components. Reliability is modeled combining the exponential and Weibull's distribution. The simulation was performed with the aim of corrective maintenance and installation of the continuous monitoring system of the most critical components. Simulation Dynamic System (SDS) method and VENSIM PLE software was used to simulate the cost. In this way, significant savings in maintenance costs will be achieved with a small initial investment.

QFD method has been applied mainly in industrial companies. The service is intangible product that has its own specificities, and the market of hotel services in our country is becoming saturated. The aim of this paper is the identification of the most important quality characteristics (technical characteristics) of the hotel service and the direction of the hotel management activities to those characteristics that can be related to the highest number of stated customer requirements. Therefore, the result of the research is to define the key characteristics of the service quality and key activities in the design of the service that lead to customer satisfaction and achieving a competitive advantage in the market. Considering the results of the previous QFD method research, especially in the domain of this type of services, and especially in our country, one might say that even a small contribution to this matter is visible and could give impetus, not only for further research in this field, but also for the concrete application of the obtained solutions.

The burgeoning field of Machine Learning (ML) has revolutionized various aspects of our lives. However, the reliance on vast amounts of data, often containing personal information, raises concerns about individual privacy. Striking a balance between effective ML model training and protecting sensitive data is crucial for responsible development and ethical implementation. This paper explores the challenges and potential solutions for preserving privacy in ML training, focusing on differential privacy (DP). The advantages of implementing DP in ML training include robust protection of individual data, enabling meaningful insights from large datasets while maintaining privacy. This is essential for ethical and responsible data usage in machine learning applications. However, DP in ML training presents challenges including scalability issues and trade-offs between utility and privacy. The paper also covers the mathematical mechanisms of Laplace and Gaussian and their noise addition, followed by a comparative analysis of their efficiency within the dataset.

Companies are moving towards the cloud more than ever, and startups are getting full support from cloud providers in terms of consulting and credits, with developers adopting new programming models shifting further away from traditional technologies. However, teaching cloud computing is still a major undertaking, as it is still difficult choosing the right tools, learning platforms, and creating curriculums to cover such a wide body of knowledge. One of the newest additions to teaching cloud is the AWS Academy curriculum and learner labs and long-running labs. In this paper, the results of implementing the AWS Academy with a hybrid model at Faculty of Technical Sciences are observed. Post-semester evaluation showed up that use of this initiative’s resources can fully support an introductory course in cloud computing. However the proper adaptation is needed to fully utilise the platform and achieve the learning goals