Due to the proliferation of large language models (LLMs) and their widespread use in applications such as ChatGPT, there has been a significant increase in interest in AI over the past year. Multiple researchers have raised the question: how will AI be applied and in what areas? Programming, including the generation, interpretation, analysis, and documentation of static program code based on promptsis one of the most promising fields. With the GPT API, we have explored a new aspect of this: static analysis of the source code of front-end applications at the endpoints of the data path. Our focus was the detection of the CWE-653 vulnerability—inadequately isolated sensitive code segments that could lead to unauthorized access or data leakage. This type of vulnerability detection consists of the detection of code segments dealing with sensitive data and the categorization of the isolation and protection levels of those segments that were previously not feasible without human intervention. However, we believed that the interpretive capabilities of GPT models could be explored to create a set of prompts to detect these cases on a file-by-file basis for the applications under study, and the efficiency of the method could pave the way for additional analysis tasks that were previously unavailable for automation. In the introduction to our paper, we characterize in detail the problem space of vulnerability and weakness detection, the challenges of the domain, and the advances that have been achieved in similarly complex areas using GPT or other LLMs. Then, we present our methodology, which includes our classification of sensitive data and protection levels. This is followed by the process of preprocessing, analyzing, and evaluating static code. This was achieved through a series of GPT prompts containing parts of static source code, utilizing few-shot examples and chain-of-thought techniques that detected sensitive code segments and mapped the complex code base into manageable JSON structures.Finally, we present our findings and evaluation of the open source project analysis, comparing the results of the GPT-based pipelines with manual evaluations, highlighting that the field yields a high research value. The results show a vulnerability detection rate for this particular type of model of 88.76%, among others.

Background/Objectives: For the rapid, objective characterization of the physiological stress response, there is currently no generally recognized standard. The stress measurement methods used in practice (e.g., for psychological measures of stress) are often subjective, or in the case of biological markers (e.g., cortisol, amylase), they usually require a blood test. For this reason, the use of heart rate variability (HRV) to characterize stress has recently come to the fore. HRV is the variability in the length of heartbeat intervals, which indicates the ability of the heart to respond to various physiological and environmental stimuli. However, the conventional HRV metrics are not corrected for heart rate dependence; hence, they fail to fully account for the complex physiology of stress and relaxation. In order to remedy this problem, here we introduce a novel HRV parameter, the normalized variability derived from an RMSSD “Master Curve”, and we compare it with the conventional metrics. Methods: In Study 1, the relaxation state was induced either by heart rate variability biofeedback training (N = 21) or by habitual relaxation (N = 21), while in Study 2 (N = 9), the Socially Evaluated Cold Pressor Test and the Socially Evaluated Stroop Test were used to induce stress in the subject. For a statistical evaluation of the data, the Kolmogorov–Smirnov test was used to compare the distributions of mean HR, log(RMSSD), log(SDNN), and normalized variability before, during, and after relaxation and stress. Results: The results of this study indicate that while log(RMSSD) and log(SDNN) did not change significantly, the normalized variability did undergo a significant change both in relaxation states and in stress states induced by the Socially Evaluated Cold Pressor Test. Conclusions: Overall, we suggest this novel type of normalized variability ought to be used as a sensitive stress indicator, and in general, for the characterization of the complex processes of the vegetative nervous system.

(1) Background and Goal: Several studies have investigated the association of sleep, diurnal patterns, and circadian rhythms with the presence and with the risk states of mental illnesses such as schizophrenia and bipolar disorder. The goal of our study was to examine actigraphic measures to identify features that can be extracted from them so that a machine learning model can detect premorbid latent liabilities for schizotypy and bipolarity. (2) Methods: Our team developed a small wrist-worn measurement device that collects and identifies actigraphic data based on an accelerometer. The sensors were used by carefully selected healthy participants who were divided into three groups: Control Group (C), Cyclothymia Factor Group (CFG), and Positive Schizotypy Factor Group (PSF). From the data they collected, our team performed data cleaning operations and then used the extracted metrics to generate the feature combinations deemed most effective, along with three machine learning algorithms for categorization. (3) Results: By conducting the training, we were able to identify a set of mildly correlated traits and their order of importance based on the Shapley value that had the greatest impact on the detection of bipolarity and schizotypy according to the logistic regression, Light Gradient Boost, and Random Forest algorithms. (4) Conclusions: These results were successfully compared to the results of other researchers; we had a similar differentiation in features used by others, and successfully developed new ones that might be a good complement for further research. In the future, identifying these traits may help us identify people at risk from mental disorders early in a cost-effective, automated way.

Rapid advances in text-to-image (T2I) generative models have significantly enhanced visual content creation. However, evaluating these models remains challenging, particularly when assessing their ability to handle complex textual content. The primary aim of this research is to develop a systematic evaluation framework for assessing T2I models’ capabilities in generating specialized content, with emphasis on measuring text rendering accuracy and identifying model limitations across diverse domains. The framework utilizes carefully crafted prompts that require precise formatting, semantic alignment, and compositional reasoning to evaluate model performance. Our evaluation methodology encompasses a comprehensive assessment across many critical domains: mathematical equations, chemical diagrams, programming code, flowcharts, multi-line text, and paragraphs, with each domain tested through specifically designed challenge sets. GPT-4 serves as an automated evaluator, assessing outputs based on key metrics such as text accuracy, readability, formatting consistency, visual design, contextual relevance, and error recovery. Weighted scores generated by GPT-4 are compared with human evaluations to measure alignment and reliability. The results reveal that current T2I models face significant challenges with tasks requiring structural precision and domain-specific accuracy. Notable difficulties include symbol alignment in equations, bond angles in chemical diagrams, syntactical correctness in code, and the generation of coherent multi-line text and paragraphs. This study advances our understanding of fundamental limitations in T2I model architectures while establishing a novel framework for the systematic evaluation of text rendering capabilities. Despite these limitations, the proposed benchmark provides a clear pathway for evaluating and tracking improvements in T2I models, establishing a standardized framework for assessing their ability to generate accurate and reliable structured content for specialized applications.

Architectural design patterns are essential in software development because they offer proven solutions to large-scale structural problems in software systems and enable developers to create software that is more maintainable, scalable, and comprehensible. Model-View-Whatever (MVW) design patterns are prevalent in many areas of software development, but their use in Web development is on the rise. There are numerous subtypes of MVW design patterns applicable to Web systems, but there is no exhaustive listing of them. Additionally, it is unclear how these subtypes can be utilized in contemporary Web development, as their usage is typically unconscious. Here, we discuss and define the most prevalent MVW design patterns used in Web development, as well as provide Angular framework examples and guidance on when to employ a particular design pattern. On the premise of the primary characteristics of design patterns, we created a rule system that large language models (LLMs) can comprehend without doubt. Here, we demonstrate how effectively Generative Pre-trained Transformer (GPT) models can identify various design patterns based on our principles and verify the quality of our recommendations. Together, our solution and GPT models constitute an effective natural language processing (NLP) solution capable of detecting MVW design patterns in Angular projects with an average accuracy of 90%.

Biofeedback (BF) therapy methods have evolved considerably in recent years. The best known is biofeedback training based on heart rate variability (HRV), which is used to treat asthma, depression, stress, and anxiety, among other conditions, by synchronizing the rhythm of breathing and heartbeat. The aim of our research was to develop a methodology and test its applicability using photoplethysmographs and smartphones to conduct biofeedback sessions for frontline healthcare workers under their everyday stressful conditions. Our hypothesis is that such a methodology is not only comparable to traditional training itself, but can make regular sessions increasingly effective in reducing real-life stress by providing appropriate feedback to the subject. The sample consisted 28 participants. Our proprietary method based on HRV biofeedback is able to determine the resonance frequency of the subjects, i.e., the number at which the pulse and respiration are in sync. Our research app then uses visual feedback to help the subject reach this frequency, which, if maintained, can significantly reduce stress. By comparing BF with Free relaxation, we conclude that BF does not lose effectiveness over time and repetitions, but increases it. This paper is our pilot study in which we discuss the method used to select participants, the development and operation of the protocol and algorithm, and present and analyze the results obtained. The showcased results demonstrate our hypothesis that purely IT-based relaxation techniques can effectively compete with spontaneous relaxation through biofeedback. This provides a basis for further investigation and development of the methodology and its widespread use to effectively reduce workplace stress.