ABSTRACT. This talk examines the formation and effectiveness of international climate treaties in the context of anthropogenic climate change. The main challenge in achieving global cooperation is the lack of a supranational enforcement mechanism. Consequently, treaties must be self-enforcing to ensure that individual countries benefit from compliance. Game theory provides a valuable framework for analyzing these treaties. The prisoner’s dilemma serves as a fundamental example, illustrating the tension between individual and collective interests. Recent research has examined the effects of tipping points and asymmetric countries on treaty formation. While a tipping point with a certain threshold can facilitate cooperation among all countries, uncertainty about the threshold can lead to the opposite result. Similarly, asymmetries in abatement costs or climate change impacts can have different consequences. Understanding these mechanisms is crucial for designing effective international climate policy. By applying game theory, policymakers can identify strategies that foster cooperation and mitigate the challenges posed by climate change.

ABSTRACT. In this position paper, we present our approach and early results in engineering an open research knowledge graph for a scholarly domain. The domain of Anti-Corruption has been chosen as the use case as it is a vibrantly developing field of scholarly research at the intersection of several fields and research communities, such as Legal, Information Science, Data Analytics, Governance, etc. Furthermore, having a methodologically sound and knowledge-based approach for anti-corruption is in demand in Ukraine on its way toward becoming a member of the European Union. Our approach for building the knowledge graph is based on the use of terminology saturation analysis that ensures the representatives of the used literature sample for knowledge extraction. For building knowledge representations from the recognized terminology, a semi-automated approach with a human in the loop is exploited, including the use of LLMs and zero-shot prompt engineering. The results are further cross-validated using human experts.

ABSTRACT. In the fast-paced modern world, where information is one of the most necessary and crucial resources, and the methods of its collection and processing are evolving at an incredible speed, every business requires swift, accurate, and secure data analysis to address questions and make decisions. From understanding the current state of affairs in a company to complex calculations of potential risks and consequences of decision-making process. As AI has become an indispensable component of life, and its primary focus is data processing. The purpose of the research is to develop a system that provides users with access to a collection of data in a user-friendly, integrated manner to enhance evaluation tasks and decision-making processes. We have posed the research question of whether it is possible to optimize the process of executing a request from the moment of its creation to the requester's get a response, without violating security and other company policies. Through examples, we will meticulously examine potential solutions and analyse various architectural approaches for their implementation, identifying the positive and negative aspects of each. Special attention will be given to optimization, security, and potential issues.

ABSTRACT. Vulnerabilities in smart contracts on the Ethereum platform attract significant attention from both the scientific and professional communities due to their potential to cause substantial financial losses. Among these, the reentrancy attack is particularly notorious for its ability to manipulate the execution flow and reactivate vulnerable functions within a smart contract, thereby disrupting intended operations and causing damage through unforeseen actions. This work aims to systematize, simplify, visualize, and extend existing knowledge on this topic. A thorough analysis of the 'Single-Function Reentrancy Attack' is conducted, during which various defense methods are meticulously investigated and systematically organized. The research methodology encompasses a literature review, code analysis of vulnerable and attacking contracts, and testing on models adapted for this paper. An important aspect of this paper is its focus on the practical testing and understanding of vulnerabilities, allowing readers to verify the experiments and validate the results independently. The examination of the implementation of vulnerable and attackable contracts reveals subtle aspects of code execution flow on the Ethereum Virtual Machine, enhanced by visual aids. This paper offers a unique analytical perspective and emphasizes the necessity of continuous analysis and updating of security strategies, as well as the development of new security tools, including automated solutions, to keep pace with rapidly evolving threats.

ABSTRACT. A migration of computations from local computers or corporate networks to the ``cloud'' has recently become a widespread trend in the development of information technology. This trend poses new challenges for both computer science in general and software engineering in particular. A modern software solution is now not merely a solution for an isolated computational unit, nor is it just a solution for a complex of computational units with shared memory. It is rather a distributed software solution. However, the developer of a distributed software solution is in a situation of greater uncertainty if compared with the developer of a local software solution. Hence, the risk of making a design error is ever-increasing for the latter. Thus, the efficiency challenge of verifying and validating a software solution is yet more significant for this kind of development. The difficulty of addressing this challenge is also caused by the fact that any instrumental code distorts the distributed software's behavior. Thus, the prospective way to meet the challenge is to create a toolkit for supporting both the traditional dynamic software analysis and the static (formal) one. To address the challenges posed by cloud computing, this paper introduces a novel approach that combines formal methods with simulation modeling. It presents and grounds a general mathematical model that can be used as the original point for implementing such a toolkit.

ABSTRACT. Deepfake audio technology, while beneficial for entertainment and assistive technology, poses significant threats to societal trust and security, including the dissemination of misinformation and impersonation risks. To address these challenges, this paper proposes a novel approach that combines Sinc and wavelet filters in the feature extraction layer of the RawNet2 architecture. Experimental results demonstrate that the networks trained with these combined filters show better generalization capabilities across diverse datasets than the original RawNet2 architecture. They consistently outperform in deepfake audio detection, showcasing their effectiveness in capturing nuanced features present in spoof audio signals. However, further research and refinement are necessary for optimal performance across all datasets. Future research directions include investigating optimal combinations of wavelets for deepfake audio detection and exploring other variations or combinations of filters to improve detection accuracy. Overall, the proposed approach offers a promising solution for detecting and mitigating the risks associated with deepfake audio, contributing to developing more robust and reliable deepfake detection systems for real-world applications.

ABSTRACT. This study is devoted to compiling an investment portfolio based on general information about the client and a special questionnaire that determines the degree of risk appetite. The research includes a comparison of the effectiveness of various machine learning algorithms including linear regression, recurrent neural networks, decision trees, and Google Simple ML service. While most investment portfolio construction approaches are based on information about past assets price movements, the approach described in this paper proposes the application of machine learning algorithms to determine the shares of financial instruments’ types in the portfolio (e.g., Commodities, High Yield Bonds, etc.). The novelty of our approach lies in forecasting the shares of financial asset classes based on a real dataset of various characteristics of new investors, as opposed to existing studies that focus on rebalancing an already existing portfolio. The results of this investigation have practical applications in the automated generation of personalized investment portfolios in Robo-Advisor services.

ABSTRACT. The identification of the types of risks is determined by utilizing the financial indicators of the 10-Q reports. However, we are unaware of studies that simultaneously analyze financial performance and text sentiment of 10-Q reports in the context of stock price dynamics. Research results show a statistically significant positive relationship between sentiment and the S&P 500 market index. In times of crisis in the market, the reaction of stock prices to news is even more pronounced. Facilitating the processing of unstructured data is particularly important since, in many cases, intelligent workers are not replaced by technology. On the contrary, their work increases, and decision support system allows for a more in-depth task analysis. The purpose of this paper is to find the relationship between stock prices, financial indicators from the quarterly report, and the results of the sentiment analysis of this report. The paper examines stock price forecasting models and identifies how the current research addresses a gap in stock price forecasting. From the reports of analysts, when analyzing sentiments, the company's financial indicators are not analyzed, but only the text of the reports. Our advanced approach combines quantitative and textual information to analyze reports regarding their impact on the company's share price. The presented approach can be helpful for the manager of clients' investment assets to support decision-making regarding the rebalancing of the investment portfolio.