Boyer Moore string-match framework for a hybrid short message service spam filtering technique

Advances in technology and the proliferation of mobile device have continued to advance the ubiquitous nature of computing alongside their many prowess and improved features it brings as a disruptive technology to aid information sharing amongst many online users. This popularity, usage and adoption ease, mobility, and portability of the mobile smartphone devices have allowed for its acceptability and popularity. Mobile smartphones continue to adopt the use of short messages services accompanied with a scenario for spamming to thrive. Spams are unsolicited message or inappropriate contents. An effective spam filter studies are limited as short-text message service (SMS) are 140bytes, 160-characters, and rippled with abbreviation and slangs that further inhibits the effective training of models. The study proposes a string match algorithm used as deep learning ensemble on a hybrid spam filtering technique to normalize noisy features, expand text and use semantic dictionaries of disambiguation to train underlying learning heuristics and effectively classify SMS into legitimate and spam classes. Study uses a profile hidden Markov network to select and train the network structure and employs the deep neural network as a classifier network structure. Model achieves an accuracy of 97% with an error rate of 1.2%.

MODELING, ANALYSIS AND COUNTERING SCENARIOS OF PREPARING COMPUTER ATTACKS REALIZED BY THE GROUP APT29 IN DISTRIBUTED COMPUTER SYSTEMS

Статья посвящена моделированию компьютерных атак на распределённые корпоративные компьютерные системы, на примере действий группировки Advanced Persistent Threat 29 (APT29). В статье предлагается подход моделирования способов, реализуемых указанной группировкой, а также мер защиты от них. Подход основан на использовании аппарата сетей Петри, а также сведений о технических приёмах, предоставляемых в рамках проекта MITRE ATT&CK. Разработанные модели учитывают связи по условиям и последствиям действий, совершаемых группировкой APT29 в ходе атак на распределённые корпоративные системы. Также в статье продемонстрирована возможность наращивания модели за счёт включения в неё моделей мер защиты от рассмотренных способов реализации компьютерных атак. Предлагаемые модели могут быть дополнены за счёт моделирования новых способов реализации компьютерных атак, используемых другими кибергруппировками. Кроме того, модели могут быть расширены до моделей сети Петри-Маркова путём реализации частным методик расчёта вероятностно-временных характеристик для фрагментов предлагаемых моделей. The article is devoted to modeling computer attacks on distributed corporate computer systems, using the example of the actions of the Advanced Persistent Threat 29 (APT29) group. The article proposes an approach to modeling the methods implemented by this grouping, as well as measures to protect against them. The approach is based on Petri nets and information about the techniques (MITRE ATT&CK project). The developed models take into account the relationship between the conditions and consequences of actions committed by the APT29 group during attacks on distributed enterprise systems. The article also demonstrates the possibility of increasing the model by including models of protection measures against the considered methods of implementing computer attacks. The proposed models can be supplemented by modeling new ways of implementing computer attacks used by other cyber groups. In addition, the models can be extended to Petri-Markov network models by implementing special methods for calculating probabilistic-time characteristics for fragments of the proposed models.

Analysis of the Development Situation and Forecasting of Development of Emergency Situations in Socio-Technical Systems

In this chapter, socio-technical analysis of Air Navigation System (ANS) has hold in the result of which the heterogeneous factors of professional and non-professional activities influencing on the decision-making (DM) of ANS's human-operator (Н-О) in expected and unexpected aircraft's (АС) operating conditions have classified, systematically compiled and formalized. The method of generalization of heterogeneous factors, which allows taking into account the structural hierarchy, heterogeneity, dynamic instability of factors of professional and non-professional activity influencing on the ANS's H-O DM has developed, the conditions for their evaluation have determined. The vector of actions of the ANS's H-O in the expected and unexpected AC operating conditions, taking into account the model of the operator's behaviour, has considered. The authors have obtained the models of bipolar choice of operator of Socio-Technical System (STS) for using of reflexion theory and Markov network. They present the results of choosing in the direction of positive, negative pole, a mixed choice and forecasting of development of the situation. The authors demonstrate the methodology for analysis of flight situation development using GERT's and Markov's networks.

Models of Decision-Making Operators of Socio-Technical System

In this chapter, the authors present Air Navigation System (ANS) as a Socio-technical System (STS). The authors present models of decision making (DM) operators of STS, such as the deterministic models obtained for using network planning; the stochastic models obtained for using decision-tree; models in uncertainty obtained for using criteria Vald, Laplace, Savage, Hurwicz and other. The authors presented also DM models of operators in ANS, such as the neural network models, fuzzy models, the Markov network models, GERT-models for modelling and forecasting of behavioral activity of ANS's Human-operator (H-O) in flight emergencies situation. The scenarios of developing a flight situation in case of selecting either the positive or negative pole in accordance with the reflexive theory have been obtained. They demonstrate some examples with DM's deterministic and stochastic models for engineers, pilots, air traffic controllers, Unmanned Aerial Vehicle (UAV) operators, managers etc. In addition, the chapter presents some examples of DM models developed by the author and students at National Aviation University.

Deep time-delay Markov network for prediction and modeling the stress and emotions state transition

To recognize stress and emotion, most of the existing methods only observe and analyze speech patterns from present-time features. However, an emotion (especially for stress) can change because it was triggered by an event while speaking. To address this issue, we propose a novel method for predicting stress and emotions by analyzing prior emotional states. We named this method the deep time-delay Markov network (DTMN). Structurally, the proposed DTMN contains a hidden Markov model (HMM) and a time-delay neural network (TDNN). We evaluated the effectiveness of the proposed DTMN by comparing it with several state transition methods in predicting an emotional state from time-series (sequences) speech data of the SUSAS dataset. The experimental results show that the proposed DTMN can accurately predict present emotional states by outperforming the baseline systems in terms of the prediction error rate (PER). We then modeled the emotional state transition using a finite Markov chain based on the prediction result. We also conducted an ablation experiment to observe the effect of different HMM values and TDNN parameters on the prediction result and the computational training time of the proposed DTMN.