scholarly journals Phishing Website Detection Based on Deep Convolutional Neural Network and Random Forest Ensemble Learning

Sensors ◽  
2021 ◽  
Vol 21 (24) ◽  
pp. 8281
Author(s):  
Rundong Yang ◽  
Kangfeng Zheng ◽  
Bin Wu ◽  
Chunhua Wu ◽  
Xiujuan Wang

Phishing has become one of the biggest and most effective cyber threats, causing hundreds of millions of dollars in losses and millions of data breaches every year. Currently, anti-phishing techniques require experts to extract phishing sites features and use third-party services to detect phishing sites. These techniques have some limitations, one of which is that extracting phishing features requires expertise and is time-consuming. Second, the use of third-party services delays the detection of phishing sites. Hence, this paper proposes an integrated phishing website detection method based on convolutional neural networks (CNN) and random forest (RF). The method can predict the legitimacy of URLs without accessing the web content or using third-party services. The proposed technique uses character embedding techniques to convert URLs into fixed-size matrices, extract features at different levels using CNN models, classify multi-level features using multiple RF classifiers, and, finally, output prediction results using a winner-take-all approach. On our dataset, a 99.35% accuracy rate was achieved using the proposed model. An accuracy rate of 99.26% was achieved on the benchmark data, much higher than that of the existing extreme model.

2020 ◽  
Vol 2020 ◽  
pp. 1-10 ◽  
Author(s):  
Alper Egitmen ◽  
Irfan Bulut ◽  
R. Can Aygun ◽  
A. Bilge Gunduz ◽  
Omer Seyrekbasan ◽  
...  

Android malware detection is an important research topic in the security area. There are a variety of existing malware detection models based on static and dynamic malware analysis. However, most of these models are not very successful when it comes to evasive malware detection. In this study, we aimed to create a malware detection model based on a natural language model called skip-gram to detect evasive malware with the highest accuracy rate possible. In order to train and test our proposed model, we used an up-to-date malware dataset called Argus Android Malware Dataset (AMD) since the AMD contains various evasive malware families and detailed information about them. Meanwhile, for the benign samples, we used Comodo Android Benign Dataset. Our proposed model starts with extracting skip-gram-based features from instruction sequences of Android applications. Then it applies several machine learning algorithms to classify samples as benign or malware. We tested our proposed model with two different scenarios. In the first scenario, the random forest-based classifier performed with 95.64% detection accuracy on the entire dataset and 95% detection accuracy against evasive only samples. In the second scenario, we created a test dataset that contained zero-day malware samples only. For the training set, we did not use any sample that belongs to the malware families in the test set. The random forest-based model performed with 37.36% accuracy rate against zero-day malware. In addition, we compared our proposed model’s malware detection performance against several commercial antimalware applications using VirusTotal API. Our model outperformed 7 out of 10 antimalware applications and tied with one of them on the same test scenario.


2019 ◽  
Vol 8 (4) ◽  
pp. 7288-7292

Fraud detection in credit card transactions is one of the major requirements of the current business scenario due to the huge amount of losses associated with the domain. This work presents a multi-level model that can provide highly effective fraud detection in credit card transactions. The model is based on the amount for which the transaction is committed. The proposed MLFD model identifies the nature of the transaction and depending on the significance level of the transaction, the appropriate learning model is selected. Experiments were performed with the standard benchmark data and comparisons were performed with existing model in literature. Results shows that the proposed model exhibits high performance compared to the existing model.


Author(s):  
Aleksandra A. Talanina ◽  

Functional and stylistic studies give us an idea of linguistic features of speech products, thus enabling style identification. These specific features become most recognizable when comparing styles. Discourse studies, on the contrary, are mainly focused on understanding and describing basic factors of creating a form of a literary language (style) and factors that determine the characteristics of speech products in individual situations within a socially significant sphere. This article presents an analysis of the logical and compositional organization of the lecture as a genre of academic discourse, taking a university lecture from M. Mamardashvili’s course on M. Proust as an example. The specific nature of the lecture genre in academic discourse is determined by its basic function in the teaching process implemented in direct dialogue with the audience. The research is based on the thesis that a lecture is an event that can be analysed using the concept of chronotope. The use of this concept beyond the analysis of fiction is relevant since spatiotemporal coordination is mandatory for any speech product, regardless of the sphere it is created in or the functions it performs. The main feature of the lecture chronotope is multi-level organization, since a lecture has its own internal spatiotemporal coordinates. The lecture chronotope is explicated at different levels of the text (compositional, lexical and grammatical), which are interconnected. Considering this, two interconnected frameworks of the lecture – structural and semantic – are singled out; they provide the logical and compositional organization of the material, which is important to ensure students’ understanding.


Author(s):  
Sona N. Golder ◽  
Ignacio Lago ◽  
André Blais ◽  
Elisabeth Gidengil ◽  
Thomas Gschwend

Voters face different incentives to turn out to vote in one electoral arena versus another. Although turnout is lowest in European elections, it is found that the turnout is only slightly lower in regional than in national elections. Standard accounts suggest that the importance of an election, in terms of the policy-making power of the body to be elected, drives variation in turnout across elections at different levels. This chapter argues that this is only part of the story, and that voter attachment to a particular level also matters. Not all voters feel connected to each electoral arena in the same way. Although for some, their identity and the issues they most care about are linked to politics at the national level, for others, the regional or European level may offer the political community and political issues that most resonate with them.


Author(s):  
Sona N. Golder ◽  
Ignacio Lago ◽  
André Blais ◽  
Elisabeth Gidengil ◽  
Thomas Gschwend

This chapter argues that individual voting behaviour and the strategies chosen by political parties across multiple electoral arenas should be considered jointly. Existing literature points to the importance of an election as a major driving force in voting behaviour, but it is argued that voters and parties may differ in their assessments of the importance of elections at different levels. The chapter discusses how the effect of the importance of an electoral arena, for both voter and party behaviour, will be conditioned by electoral institutions and characteristics of parties and the party system, in addition to individual voter characteristics contributing to it.


2021 ◽  
Vol 15 (1) ◽  
pp. 151-160
Author(s):  
Hemant P. Kasturiwale ◽  
Sujata N. Kale

The Autonomous Nervous System (ANS) controls the nervous system and Heart Rate Variability (HRV) can be used as a diagnostic tool to diagnose heart defects. HRV can be classified into linear and nonlinear HRV indices which are used mostly to measure the efficiency of the model. For prediction of cardiac diseases, the selection and extraction features of machine learning model are effective. The available model used till date is based on HRV indices to predict the cardiac diseases accurately. The model could hardly throw light on specifics of indices, selection process and stability of the model. The proposed model is developed considering all facet electrocardiogram amplitude (ECG), frequency components, sampling frequency, extraction methods and acquisition techniques. The machine learning based model and its performance shall be tested using the standard BioSignal method, both on the data available and on the data obtained by the author. This is unique model developed by considering the vast number of mixtures sets and more than four complex cardiac classes. The statistical analysis is performed on a variety of databases such as MIT/BIH Normal Sinus Rhythm (NSR), MIT/BIH Arrhythmia (AR) and MIT/BIH Atrial Fibrillation (AF) and Peripheral Pule Analyser using feature compatibility techniques. The classifiers are trained for prediction with approximately 40000 sets of parameters. The proposed model reaches an average accuracy of 97.87 percent and is sensitive and précised. The best features are chosen from the different HRV features that will be used for classification. The present model was checked under all possible subject scenarios, such as the raw database and the non-ECG signal. In this sense, robustness is defined not only by the specificity parameter, but also by other measuring output parameters. Support Vector Machine (SVM), K-nearest Neighbour (KNN), Ensemble Adaboost (EAB) with Random Forest (RF) are tested in a 5% higher precision band and a lower band configuration. The Random Forest has produced better results, and its robustness has been established.


Energies ◽  
2021 ◽  
Vol 14 (4) ◽  
pp. 849
Author(s):  
Sung-An Kim

A modeling of a turbo air compressor system (TACS), with a multi-level inverter for driving variable speed, combining an electrical model of an electric motor drive system (EMDS) and a mechanical model of a turbo air compressor, is essential to accurately analyze dynamics characteristics. Compared to the mechanical model, the electrical model has a short sampling time due to the high frequency switching operation of the numerous power semiconductors inside the multi-level inverter. This causes the problem of increased computational time for dynamic characteristics analysis of TACS. To solve this problem, the conventional model of the multi-level inverter has been proposed to simplify the switching operation of the power semiconductors, however it has low accuracy because it does not consider pulse width modulation (PWM) operation. Therefore, this paper proposes an improved modeling of the multi-level inverter for TACS to reduce computational time and improve the accuracy of electrical and mechanical responses. In order to verify the reduced computational time of the proposed model, the conventional model using the simplified model is compared and analyzed using an electronic circuit simulation software PSIM. Then, the improved accuracy of the proposed model is verified by comparison with the experimental results.


Author(s):  
D.M. Belousov ◽  

Analysis of the economic and social situation allows for the conclusion that the world is entering an era of global instability and contradictions. There is clearly a crisis of compensatory and basic institutions. Humans cease to be the subjects of the historical process and instead are becoming the object of control. Contradictions are sharply increasing at different levels. We are witnessing the conflict between labor and capital related to the national nature of labor and the global nature of capital. Production, security and regional applied science are changing, but financial and institutional systems remain global. Information and trade wars are intensifying. During a multi-level crisis, it is difficult to predict what a new social order will be like, but the transition to it will be difficult and highly possibly rife with (macro-) regional conflicts.


2018 ◽  
Vol 10 (9) ◽  
pp. 3272 ◽  
Author(s):  
Elena-Teodora Miron ◽  
Anca Purcarea ◽  
Olivia Negoita

Third-party innovators, i.e., complementors, in platform enterprises develop and commercialize add-on products which are one of the main attraction points for customers. To ensure a sustainable evolution of the enterprise, the platform owner needs to attract and retain high-quality third-party innovators. We posit that the transaction costs incurred upon joining the enterprise as well as the controls imposed by the platform owner throughout the development and commercialization process shape the innovator’s perceived risk and influence his decision on whether to join or not. Based on a literature review, the paper at hand proposes a conceptual model for complementors to assess their perceived risk and subsequently evaluates the model in a case study of a platform enterprise for IT-based modelling tools. While some of the propositions are validated, i.e., that informational controls decrease the perceived environmental uncertainty and implicitly the perceived risks, other propositions, such as the fact that asset specificity is a deterrent to entering the platform enterprise could not be validated. Further case studies are necessary to provide a conclusive proof of the proposed model.


2011 ◽  
Vol 1 ◽  
pp. 375-380
Author(s):  
Shu Ai Wan ◽  
Kai Fang Yang ◽  
Hai Yong Zhou

In this paper the important issue of multimedia quality evaluation is concerned, given the unimodal quality of audio and video. Firstly, the quality integration model recommended in G.1070 is evaluated using experimental results. Theoretical analyses aide empirical observations suggest that the constant coefficients used in the G.1070 model should actually be piecewise adjusted for different levels of audio and visual quality. Then a piecewise function is proposed to perform multimedia quality integration under different levels of the audio and visual quality. Performance gain observed from experimental results substantiates the effectiveness of the proposed model.


Sign in / Sign up

Export Citation Format

Share Document