Search

Network intrusion detection is a relevant cybersecurity research field. The growing number of intrusions requires more sophisticated methods to protect computer networks. Various machine learning algorithms are used to detect network intrusions and anomalies, but their accuracy is limited. In this research, we address the problem of improving network-level intrusion detection by applying hybrid machine-learning algorithms. The paper proposes three new hybrid machine learning methods and investigates their accuracy using two publicly available datasets CSE-CIC-IDS2018 and NSW-NB-15. In order to increase the accuracy of the classification models, hyperparameter optimization was performed. The iteration method and the Chi-square χ² test were used to identify significant features of the data set. Analyzing the research results, it was found that the highest network anomaly recognition accuracy of 99.34% was achieved by applying a hybrid algorithm consisting of a decision tree, naive Bayesian, and multilayer perceptron algorithms. Achieved result is 3.13% higher than the best accuracy achieved by individual machine learning algorithms. In order to comprehensively evaluate the studied machine learning algorithms and their suitability for detecting intrusions in a computer network, the algorithms were ranked using the SCR, DR, FR ranking methods. [ABSTRACT FROM AUTHOR]

The paper examines the possibilities of speculating in exchangetraded funds by using artificial intelligence. The main goal of the research is to create a support system for speculative decisionmaking for investors operating in exchange-traded funds market. The research will be based on the theoretical aspects of artificial intelligence and speculation of exchange-traded funds. The support system is developed on the basis of reinforcement learning, the methods of synthesis, concretization and generalization were used to create and detail the system, as well as the methods of mathematical-statistical analysis were used to process them. Successful application of the chosen methodology in the design of the support system has resulted in positive trade results. Successful research broadens the boundaries for usage of deep reinforcement learning, and provides a basis for further development of the support system for exchange-traded funds. The support system put in place will shorten the time between the occurrence of a trading signal and the decision of the investor, which will help to reduce the loss of potential profits. [ABSTRACT FROM AUTHOR]

Network intrusion detection is a relevant cybersecurity research field. The growing number of intrusions requires more sophisticated methods to protect computer networks. Various machine learning algorithms are used to detect network intrusions and anomalies, but their accuracy is limited. In this research, we address the problem of improving network-level intrusion detection by applying hybrid machine-learning algorithms. The paper proposes three new hybrid machine learning methods and investigates their accuracy using two publicly available datasets CSE-CIC-IDS2018 and NSW-NB-15. In order to increase the accuracy of the classification models, hyperparameter optimization was performed. The iteration method and the Chi-square χ2 test were used to identify significant features of the data set. Analyzing the research results, it was found that the highest network anomaly recognition accuracy of 99.34% was achieved by applying a hybrid algorithm consisting of a decision tree, naive Bayesian, and multilayer perceptron algorithms. Achieved result is 3.13% higher than the best accuracy achieved by individual machine learning algorithms. In order to comprehensively evaluate the studied machine learning algorithms and their suitability for detecting intrusions in a computer network, the algorithms were ranked using the SCR, DR, FR ranking methods. Article in Lithuanian. Įsilaužimų aptikimas kompiuterių tinkluose taikant hibridinius mašininio mokymosi metodus Santrauka Viena iš aktualių kibernetinės saugos tyrimų krypčių – tai įsilaužimų arba anomalijų aptikimas kompiuterių tinkle. Įsilaužimų skaičius nuolat didėja, o taikomos įsilaužimo technikos ir metodai sudėtingėja, todėl siekiant apsaugoti kompiuterių tinklą, reikia taikyti vis sudėtingesnius apsaugos metodus. Tinklo įsilaužimams ir anomalijoms nustatyti taikomi įvairūs mašininio mokymosi algoritmai, tačiau jų tikslumas yra ribotas. Siekiama pagerinti tinklo anomalijų aptikimą, taikomi hibridiniai mašininio mokymosi algoritmai. Straipsnyje pasiūlyti trys nauji hibridiniai mašininio mokymosi algoritmai, ištirtas jų tikslumas naudojant du viešai prieinamus duomenų rinkinius, t. y. CSE-CIC-IDS2018 ir NSW-NB-15. Siekiant padidinti klasifikavimo modelių tikslumą, buvo atliktas hiperparametrų optimizavimas. Reikšmingiems duomenų rinkinio požymiams nustatyti taikytas iteracijų metodas ir Chi kvadrato χ2 testas. Analizuojant tyrimo rezultatus, nustatyta, kad aukščiausias tinklo anomalijų atpažinimo tikslumas 99,34 % buvo pasiektas taikant hibridinį algoritmą, sudarytą iš sprendimų medžio, naivaus Bajeso ir daugiasluoksnio perceptrono algoritmų rinkinio. Šis rezultatas yra 3,13 % geresnis, lyginant su geriausiu tikslumu, gautu taikant atskirus mašininio mokymosi algoritmus. Siekiant kompleksiškai įvertinti tirtus mašininio mokymosi algoritmus ir jų tinkamumą įsilaužimams kompiuterių tinkle aptikti, algoritmai buvo sureitinguoti taikant SCR, DR, FR reitingavimo metodus. Reikšminiai žodžiai: tinklo anomalijos, mašininis mokymasis, χ2 Chi kvadratu testas, hiperparametrai, hibridiniai algoritmai.

Social Media Platforms (SMPs) are currently the leading media data sources in the world; billions of people’s electronic devices have adopted these SMPs for their use. The users ‘ accounts on these platforms generate massive amounts of data daily. Data have become an essential building block for many organizations of different domains. Recently, media organizations started using social media as a principal source to collect data, mainly news. Having recognized the importance of SMPs and data availability, media organizations are not using these data efficiently. Many media organizations still use and analyze internet data, especially from social media, manually, which leads to many disadvantages. This research proposes a more efficient and automated approach to collecting information from social media. Actually, this paper proposes an integrated framework that can extract data from multiple SMPs and merge them, store them, and finally allow media workers to extract fundamental data (events) automatically and smartly from social media. The proposed framework takes input from a query and finds the following information: top tweets, total likes and retweets on this query, user’s identity, sentiment analysis, and finally, the prediction component that can classify if a particular item has classified an event or not. An advantage of this approach is to help media leaders control and track their performance in the media sector and maintain popularity on the internet. The proposed system has been validated on real datasets collected from different data sources. Findings show that this proposed system has remarkable accuracy, precision, and recall results, after evaluating different machine learning algorithms.

Artificial intelligence depends on digital devices’ performance to perform tasks regularly, requiring human intelligence, using special software to accomplish work easier and faster, carrying out data-packed tasks, and providing useful analytics or solutions. It also requires a specialized laboratory that provides high-performance computing capabilities and a technical platform for deep machine learning. These resources will enable the artificial intelligence platform to master the machine learning techniques of using, developing, simulating, predicting models, and building ready-to-use technological solutions such as analytics platforms. In general, the artificial intelligence system manipulates and manages large amounts of training data to form correlations and patterns used in building future predictions . A limited-memory artificial intelligence system can store a limited amount of information based on the data that have been processed and dealt with previously to build knowledge by memory when combined with pre-programmed data. Consequently, one may ask how artificial intelligence applications contribute to verifying the truthfulness of the media through digital media. How do they contribute to preventing the spread of misleading and false news? This study tries to answer the following question: What methods and tools are adopted by artificial intelligence to detect fake news, especially on social media platforms and depending on artificial intelligence laboratories? This paper is framed within automation control theory and by defining the needed control tools and programs to detect fake news and verify media facts.

The paper examines the possibilities of speculating in exchangetraded funds by using artificial intelligence. The main goal of the research is to create a support system for speculative decisionmaking for investors operating in exchange-traded funds market. The research will be based on the theoretical aspects of artificial intelligence and speculation of exchange-traded funds. The support system is developed on the basis of reinforcement learning, the methods of synthesis, concretization and generalization were used to create and detail the system, as well as the methods of mathematical-statistical analysis were used to process them. Successful application of the chosen methodology in the design of the support system has resulted in positive trade results. Successful research broadens the boundaries for usage of deep reinforcement learning, and provides a basis for further development of the support system for exchange-traded funds. The support system put in place will shorten the time between the occurrence of a trading signal and the decision of the investor, which will help to reduce the loss of potential profits. Article in Lithuanian. Paramos sistema spekuliavimui biržoje prekiaujamais fondais Santrauka Darbe yra nagrinėjamos spekuliavimo biržoje prekiaujamais fondais, naudojant dirbtinį intelektą, galimybės. Pagrindinis mokslinio tyrimo tikslas – remiantis dirbtinio intelekto bei biržoje prekiaujamų fondų spekuliavimo teoriniais aspektais, sukurti spekuliavimo sprendimų priėmimo paramos sistemą investuotojams, veikiantiems biržoje prekiaujamų fondų rinkoje. Paramos sistema yra kuriama remiantis sustiprintuoju mokymusi (angl. reinforcement learning), sistemai sudaryti ir detalizuoti buvo taikyti sintezės, konkretizavimo bei apibendrinimo metodai, taip pat, panaudojus susidarytą sistemą bei gavus rezultatus, jiems apdoroti taikyti matematinės-statistinės analizės metodai. Sėkmingai pritaikius pasirinktą metodologiją, sudarant paramos sistemą, buvo gauti teigiami prekybos rezultatai. Sėkmingas tyrimas išplečia giliojo sustiprintojo mokymosi taikymo suvokimo ribas bei sudaro pagrindą tolesniam biržoje prekiaujamų fondų paramos sistemos vystymui. Sudaryta paramos sistema sutrumpins sugaištamą laiką tarp prekybos signalo atsiradimo ir investuotojo sprendimo priėmimo, o tai padės sumažinti potencialaus pelno praradimą. Reikšminiai žodžiai: paramos sistema, biržoje prekiaujami fondai, spekuliavimas, dirbtinis intelektas, finansų rinka, sustiprintasis mokymasis, mašininis mokymasis.

Financial auditing cannot be imagined without the involvement of IT specialists since business processes are designed to be served by IT components such as ERP systems, online customer-facing applications, databases etc. Financial auditors therefore exposed to IT system and control reliance want to gain reasonable assurance that data and transactions stored in IT systems cannot be modified, access is controlled, and there is no suspicion of any fraud at business organizations. The paper tries to understand the current situation of IT audit involvement in financial auditing, interpret risks that parties face and provide some solutions by use of intelligent applications.