Journal of Computer and Forensic Sciences

A verifiable model of a minimal market operating sequentially, with price and time discrete

2023-07-13T14:52:07+02:00

This research presents a minimal computational market model, i.e.,a model of a trading venue, with sequential order matching, in a declarative style, and proceeds to demonstrate how some fundamental properties can be formally proved. It is a challenging task to formally certify properties for a fundamental system in any realm of human endeavor, especially for systems with infinite state space. With the recent development of theoretical frameworks based on formal logic, it is now possible (albeit very difficult) to both formalize and reason about an object system in the same language. This research derives from the previous research presented in [1], and represents a simplification to obtain a minimal model. The computational model of a minimal market, presented here in a declarative style, is of importance from the perspective of both market design and verification.

Speech Enhancement by CycleGAN Using Feature Map Regularization

2023-07-13T14:52:07+02:00

Highly promising speech enhancement results are recently obtained using an unsupervised CycleGAN approach, comparable to paired dataset neural network approach. However, very often, only a limited amount of noisy speech data is available. Therefore, a semi-supervised CycleGAN approach has been proposed, relying on augmented data samples. Another feature map regularized CycleGAN approach has also been proposed and applied in an image-style translation task, obtaining significant improvements on several standard databases. The feature map regularized CycleGAN approach is combined with the aforementioned semi-supervised learning approach and applied within a speech enhancement task. Significant improvements are obtained in terms of several standard measures using the proposed algorithm in comparison with the baseline algorithm as well as the augmented CycleGAN approach.

iThrust News Certificate: A Blockchain-Based Solution for News Verification and Reputation Management

2023-07-13T14:52:07+02:00

The proliferation of fake news and misinformation in the digital era poses a significant challenge to news organizations and content creators. In this paper, we introduce iThrust News Certificate, the architecture of an online blockchain-based solution designed to combat fake news, enhance news verification, and maintain reputation within the media ecosystem. Unlike previous attempts, iThrust News Certificate focuses on user-friendly features while ensuring transparency and reliability.

A system architecture for preventing social engineering attacks via e-mail

2023-07-13T14:52:07+02:00

Modern business and the expansion of Internet technology have caused a great growth in communication via electronic mail. Bearing in mind that the weakest link of any system is the person himself, it is precisely in this part of the system that the greatest danger of unauthorized access to ICT resources is recognized[6]. For this reason, the greatest attention regarding the protection of ICT systems should be focused on the users themselves and preventive response to phishing campaigns as the most common form of cyber attack. This paper will present the system architecture for preventive response to phishing campaigns. The architecture itself, which will be explained in more detail later in the text, consists of several different modules integrated into a whole. First, a sender analysis module, which would be based on the blacklist principle. Next, an email attachment analysis module, which would perform the functions of static and dynamic analysis of potentially malicious attachments. A link analysis module, which would include the application of CORTEX, an open source intelligence service, and finally, a text analysis module, based on statistical models.

Keywords: phishing, Cortex; analysis, cyber attack

An Application of Machine Learning Methods for Anomaly Detection in Internet Advertising

2023-07-13T14:52:07+02:00

This research deals certain issues regarding downloading data from the Internet, i.e. Internet page advertising, and certain mechanisms to take care of the integrity of the data that is put into the dedicated processing context afterwards. The work also relates to e-commerce as well as to the economy in general, as some advertising scenarios provide high error-rates with pricing, which may be unacceptable in various scenarios, such as renting or selling a home. This paper presents a brief overview of the outlier detection methods and machine learning-based classifiers which are used to determine the number of anomalies in the analyzed dataset. This work contributes to the operation of the organizations which are dealing with data accuracy and integrity, such as home renting or selling agencies.