scholarly journals An Emerging Solution for Detection of Phishing Attacks

2021 ◽  
Author(s):  
Prasanta Kumar Sahoo
Keyword(s):  
Cyber Security ◽  
Electronic Mail ◽  
Social Engineering ◽  
Machine Learning Algorithms ◽  
Security Attacks ◽  
Decision Tree Classifier ◽  
Phishing Attacks ◽  
Tree Classifier ◽  
Prevention Methods ◽  
E Mail

In this era of computer age, as more and more people use internet to carry out their day to day work so as hackers performs various security attacks on web browsers and servers to steal user’s vital data. Now Electronic mail (E-mail) is used by everyone including organizations, agency and becoming official communication for the society as a whole in day to day basis. Even though a lot of modern techniques, tools and prevention methods are being developed to secure the users vital information but still they are prone to security attacks by the fraudsters. Phishing is one such attack and its detection with high accuracy is one of the prominent research issues in the area of cyber security. Phisher fraudulently acquire confidential information like user-id, passwords, visa card and master card details through various social engineering methods. Mostly blacklist based methodology is used for detection of phishing attacks but this method has a limitation that it cannot be used for detection of white listed phishing. This chapter aims to use machine learning algorithms to classify between phishing E-mails and genuine E-mails and helps the user in detecting attacks. The architectural model proposed in this chapter is to identify phishing and use J48 decision tree classifier to classify the fake E-mail from real E-mail. The algorithm presented here goes through several stages to identify phishing attack and helps the user in a great way to protect their vital information.

scholarly journals THE PLACE OF SOCIAL ENGINEERING IN THE PROBLEM OF DATA LEAKS AND ORGANIZATIONAL ASPECTS OF CORPORATE ENVIRONMENT PROTECTION AGAINST FISHING E-MAIL ATTACKS

2021 ◽  
Vol 1 (13) ◽  
pp. 6-15
Author(s):  
Yuriy Yakymenko ◽  
Dmytro Rabchun ◽  
Mykhailo Zaporozhchenko
Keyword(s):  
Social Engineering ◽  
Corporate Environment ◽  
Phishing Attacks ◽  
Internet Users ◽  
Significant Damage ◽  
Hands On ◽  
Periodic Testing ◽  
Almost All ◽  
E Mail ◽  
Security Incidents

As the number and percentage of phishing attacks on company employees and regular users have tended to increase rapidly over the last two years, it is necessary to cover the issue of protection against this type of social engineering attacks. Throughout the pandemic, intruders are finding more and more new ways to cheat, so even experienced Internet users can become a victim to their scams. Due to the fact that e-mail is used in almost all companies, most fishing attacks use e-mail to send malicious messages. The article discusses the main methods used by attackers to conduct phishing attacks using e-mail, signs that the user has become a victim to social engineers, and provides recommendations how to increase the resilience of the corporate environment to such attacks using organizational methods. Because the user is the target of phishing attacks, and the tools built into the browser and email clients in most cases do not provide reliable protection against phishing, it is the user who poses the greatest danger to the company, because he, having become a victim of a fishing attack, can cause significant damage to the company due to his lack of competence and experience. That is why it is necessary to conduct training and periodic testing of personnel to provide resistance to targeted phishing attacks. Company employees should be familiar with the signs of phishing, examples of such attacks, the principles of working with corporate data and their responsibility. The company's management must create and communicate to the staff regulations and instructions that describe storage, processing, dissemination and transfer processes of information to third parties. Employees should also report suspicious emails, messages, calls, or people who have tried to find out valuable information to the company's security service. Raising general awareness through hands-on training will reduce the number of information security incidents caused by phishing attacks.

scholarly journals Analytical Models for Traffic Congestion and Accident Analysis

2021 ◽  
Author(s):  
Hongrui Liu ◽  
Rahul Ramachandra Shetty
Keyword(s):  
Traffic Congestion ◽  
Regression Tree ◽  
Machine Learning Algorithms ◽  
Analytical Models ◽  
Gradient Boosting ◽  
Decision Tree Classifier ◽  
The Road ◽  
Tree Classifier ◽  
Extreme Gradient Boosting ◽  
On The Road

In the US, over 38,000 people die in road crashes each year, and 2.35 million are injured or disabled, according to the statistics report from the Association for Safe International Road Travel (ASIRT) in 2020. In addition, traffic congestion keeping Americans stuck on the road wastes millions of hours and billions of dollars each year. Using statistical techniques and machine learning algorithms, this research developed accurate predictive models for traffic congestion and road accidents to increase understanding of the complex causes of these challenging issues. The research used US Accidents data consisting of 49 variables describing 4.2 million accident records from February 2016 to December 2020, as well as logistic regression, tree-based techniques such as Decision Tree Classifier and Random Forest Classifier (RF), and Extreme Gradient boosting (XG-boost) to process and train the models. These models will assist people in making smart real-time transportation decisions to improve mobility and reduce accidents.

scholarly journals QSAR Models for Active Substances Against Pseudomonas aeruginosa Using Disk-diffusion Test Data

2021 ◽  
Author(s):  
Cosmin Alexandru Bugeac ◽  
Robert Ancuceanu ◽  
Mihaela Dinu
Keyword(s):  
Pseudomonas Aeruginosa ◽  
Model Development ◽  
Qsar Model ◽  
Machine Learning Algorithms ◽  
Disk Diffusion ◽  
Support Vector ◽  
Decision Tree Classifier ◽  
K Nearest Neighbors ◽  
Disk Diffusion Test ◽  
Tree Classifier

Pseudomonas aeruginosa is a Gram-negative bacillus included among the six "ESKAPE" microbial species with an outstanding ability to "escape" currently used antibiotics and developing new antibiotics against it is of the highest priority. Whereas minimum inhibitory concentration (MIC) values against Pseudomonas aeruginosa have been used previously for QSAR model development, disk diffusion results (inhibition zones) have not been apparently used for this purpose in the literature, and we decided to explore their use in this sense. We developed multiple QSAR methods using several machine learning algorithms (Support vector classifier, K Nearest Neighbors, Random Forest Classifier, Decision Tree Classifier, AdaBoost Classifier, Logistic Regression, and Naive Bayes Classifier). The main descriptors used in building the models belonged to the families of adjacency matrix, constitutional descriptors, first highest eigenvalue of Burden matrix, centered Moreau-Broto autocorrelation, and averaged and centered Moreau-Broto autocorrelation descriptors. A total of 32 models were built, of which 28 were selected and stacked to create a meta-model. In terms of balanced accuracy, the best performance was provided by KNN, SVM and AdaBoost algorithms, but the ensemble method had slightly superior results in nested cross-validation.

scholarly journals Ensemble-Based Machine Learning for Predicting Sudden Human Fall Using Health Data

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Utkarsh Saxena ◽  
Soumen Moulik ◽  
Soumya Ranjan Nayak ◽  
Thomas Hanne ◽  
Diptendu Sinha Roy
Keyword(s):  
Machine Learning ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Majority Voting ◽  
Support Vector ◽  
Human Beings ◽  
Medical Terminology ◽  
Decision Tree Classifier ◽  
Tree Classifier ◽  
Health Parameters

We attempt to predict the accidental fall of human beings due to sudden abnormal changes in their health parameters such as blood pressure, heart rate, and sugar level. In medical terminology, this problem is known as Syncope. The primary motivation is to prevent such falls by predicting abnormal changes in these health parameters that might trigger a sudden fall. We apply various machine learning algorithms such as logistic regression, a decision tree classifier, a random forest classifier, K-Nearest Neighbours (KNN), a support vector machine, and a naive Bayes classifier on a relevant dataset and verify our results with the cross-validation method. We observe that the KNN algorithm provides the best accuracy in predicting such a fall. However, the accuracy results of some other algorithms are also very close. Thus, we move one step further and propose an ensemble model, Majority Voting, which aggregates the prediction results of multiple machine learning algorithms and finally indicates the probability of a fall that corresponds to a particular human being. The proposed ensemble algorithm yields 87.42% accuracy, which is greater than the accuracy provided by the KNN algorithm.

scholarly journals Prediction of Students’ Performance based on Academic, Behaviour, Extra and Co-Curricular Activities

Webology ◽  
2021 ◽  
Vol 18 (Special Issue 01) ◽  
pp. 262-279
Author(s):  
T. Jenitha ◽  
S. Santhi ◽  
J. Monisha Privthy Jeba
Keyword(s):  
Extracurricular Activities ◽  
Family Background ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Academic Institutions ◽  
Physical And Mental Health ◽  
Decision Tree Classifier ◽  
Academic Scholarship ◽  
Tree Classifier ◽  
Training Programmes

Since Academic institutions contain huge volume of data regarding students such as academic scores, scores in co and extracurricular activities, family annual income, family background and other supporting documents, predicting individual students performance in all aspects manually is a difficult task. The proposed work uses data mining techniques to identify students who are eligible for scholarships and other benefits. Students are classified into different categories by means of academic, behavior, extra and co-curricular activities. Machine Learning algorithms such as Naive Bayes, Decision Tree Classifier and Support Vector Machine are used for predicting the performance of the student. With the help of this proposed model parents and instructors can monitor student’s performance and they can also provide essential technical and moral support. Also this helps in providing academic scholarship and training to the students to support them financially and to enrich their knowledge. It suggests the Academic Institutions to organize induction or training programmes at the beginning of the semester. Technical training, motivational talks, Yoga, etc are organized by the institutions by keeping in mind of students physical and mental health. Considering the e-learning platforms huge volumes of data and plethora of information are generated. In this work, various learning models are constructed and their accuracies are compared to analyse which algorithm out-performs.

scholarly journals A Novel Approach to Railway Track Faults Detection Using Acoustic Analysis

Sensors ◽  
2021 ◽  
Vol 21 (18) ◽  
pp. 6221
Author(s):  
Rahman Shafique ◽  
Hafeez-Ur-Rehman Siddiqui ◽  
Furqan Rustam ◽  
Saleem Ullah ◽  
Muhammad Abubakar Siddique ◽  
...  
Keyword(s):  
Human Error ◽  
Acoustic Analysis ◽  
Detection System ◽  
Machine Learning Algorithms ◽  
Railway Track ◽  
Support Vector ◽  
Decision Tree Classifier ◽  
Traditional Procedure ◽  
Novel Approach ◽  
Tree Classifier

Regular inspection of railway track health is crucial for maintaining safe and reliable train operations. Factors, such as cracks, ballast issues, rail discontinuity, loose nuts and bolts, burnt wheels, superelevation, and misalignment developed on the rails due to non-maintenance, pre-emptive investigations and delayed detection, pose a grave danger and threats to the safe operation of rail transport. The traditional procedure of manually inspecting the rail track using a railway cart is both inefficient and prone to human error and biases. In a country like Pakistan where train accidents have taken many lives, it is not unusual to automate such approaches to avoid such accidents and save countless lives. This study aims at enhancing the traditional railway cart system to address these issues by introducing an automatic railway track fault detection system using acoustic analysis. In this regard, this study makes two important contributions: data collection on Pakistan railway tracks using acoustic signals and the application of various classification techniques to the collected data. Initially, three types of tracks are considered, including normal track, wheel burnt and superelevation, due to their common occurrence. Several well-known machine learning algorithms are applied such as support vector machines, logistic regression, random forest and decision tree classifier, in addition to deep learning models like multilayer perceptron and convolutional neural networks. Results suggest that acoustic data can help determine the track faults successfully. Results indicate that the best results are obtained by RF and DT with an accuracy of 97%.

scholarly journals Synthetic Minority Oversampling and Smote Regularised Deep Autoencoders Neural Network Techniques for Fraud Prediction in Financial Payment Services

2019 ◽  
Vol 8 (12) ◽  
pp. 3908-3915
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Financial Institutions ◽  
Fraud Detection ◽  
Machine Learning Algorithms ◽  
Decision Tree Classifier ◽  
Class Imbalance Problem ◽  
Good Recall ◽  
Tree Classifier ◽  
Payment Services

Frauds in Financial Payment Services are the most prevalent form of cybercrime. The increased growth in e-commerce and mobile payments in recent years is behind the rising incidence of fraud in financial payment services. According to "McKinsey, fraud losses throughout the world could be close to $44 billion by 2025." Every year, fraudulent card transactions causes billions of US Dollar of loss. To reduce these losses, designing effective fraud detection algorithms is essential, which depend on sophisticated machine learning methods to help investigators in fraud. For banks and financial institutions, therefore, fraud detection systems have gained excellent significance. Though the fake transactions are very low when compared to genuine transaction, care must be taken to predict it so that the financial institutions can maintain the customer integrity. As fraud is unlikely to occur compared to normal operations, we have the class imbalance problem. We applied Synthetic Minority Oversampling TEchnique (SMOTE) and the Ensemble of sampling methods(Balanced Random Forest Classifier, Balanced Bagging Classifier, Easy Ensemble Classifier, RUS Boost) to Ensemble machine learning algorithms Performance assessment using sensitivity, specificity, precision, ROC area. The purpose of this article is to analyze different predictive models to see how precise they are to detect whether a transaction is a standard payment or a fraud. Instead of misclassifying a real transaction as fraud, this model seeks to improve detection of fraud. We noted that the technique of Ensemble learning using Maximum voting detects the fraud better than other classifiers. Decision Tree Classifier, Logistic Regression, Balanced Bagging classifier is combined and the proposed algorithm is OptimizedEnsembleFD Algorithm. The sample size is increased and deep learning is applied .It is found that the proposed system Smote Regularised Deep Autoencoders (SRD Autoencoders) neural network performs better with good recall and accuracy for this large dataset.

scholarly journals Prophecy on Programming Language using Machine Learning Algorithms

2021 ◽  
Vol 9 (VI) ◽  
pp. 3699-3706
Author(s):  
Komal Bhaskar Thube
Keyword(s):  
Machine Learning ◽  
Programming Language ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Computer Language ◽  
Decision Tree Classifier ◽  
Development Environment ◽  
Tree Classifier ◽  
Develop Software ◽  
Neighbor Classifier

A programming language is a computer language developers use to develop software programs, scripts, or other sets of instruction for computers to execute. It is difficult to determine which programming language is widely used. In our work, I have analyzed and compared the classification results of various machine learning models and find out which programming language is widely used by developers. I have used Support Vector Machine (SVM), K neighbor classifier (KNN),Decision Tree Classifier(CART) for our comparative study. My task is to analyze different data and to classify them for the efficiency of each algorithm in terms of accuracy, precision, recall, and F1 Score. My best accuracy was 94.29% percent which was found using SVM. These techniques are coded in python and executed in Jupyter NoteBook, the Scientific Python Development Environment. Our experiments have shown that SVM is the best for predictive analysis and from our study that SVM is the well-suited algorithm for the prediction of the most widely used programming language.

scholarly journals Detailed Analysis of Intrusion Detection using Machine Learning Algorithms

2020 ◽  
Vol 9 (1) ◽  
pp. 1894-1899 ◽  
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Svm Classifier ◽  
Learning Approaches ◽  
Decision Tree Classifier ◽  
Internet Users ◽  
Tree Classifier ◽  
Challenging Tasks

The number of internet users has increased exponentially over the years and so have increased intrusive activities significantly. To detect an intrusion attack in a system connected over a network is one of the most challenging tasks in today’s world. A significant number of techniques have been developed which are based on machine learning approaches to detect these intrusion attacks. Even though these techniques are good, they are not good enough to detect all kinds of attacks. In this paper, the analysis of different machine learning algorithm will be performed on the NSL-KDD dataset with pre-processing steps like One-hot encoding, feature selection and random sampling to use in different machine learning models to find the best performing model to detect these attacks. The attacks are from the datasets are classified into four types of attacks: Probe, DoS, U2R, R2L while the non- attack is the Normal. The dataset is in two parts: KDD-Train and KDD-Test. The dataset is trained and tested to find accuracy and understand the performance of different machine learning algorithms and compare them. The Machine Learning algorithms used are Naive Bayes Classifier, Decision Tree Classifier, Random Forest Classifier, KNeighbours Classifier, Logistic Regression, SVM Classifier, Voting Classifier. These techniques are compared according to their capability to detect the attacks. This comparison will help to find the algorithm which would work the best to detect different kinds of intrusion attacks.

scholarly journals Analysing Road Accident Criticality using Data mining

2019 ◽  
pp. 408-415
Author(s):  
Shahsitha Siddique V ◽  
Nithin Ramakrishnan
Keyword(s):  
Data Mining ◽  
Road Transport ◽  
Road Accident ◽  
Machine Learning Algorithms ◽  
Road Accidents ◽  
Decision Tree Classifier ◽  
Efficient Manner ◽  
Tree Classifier ◽  
Accident Severity ◽  
Accident Data

Road transport is one of the most vital forms of transportation system, connecting both long and short distances in our country. There are several attributes, which affect the intensity of a road accident like speed of the vehicle, road conditions, time of the accident etc. Analysing these attributes gives an idea about the factors lead to the severity of the accident. Data mining is a method to analyse huge amount of traffic data in an efficient manner, which gives the factors, affect the road accidents. Several machine learning algorithms can be used to find the relation between traffic attributes the lead to the severity of the accidents. In this work, we use three methods for predicting accident criticality. First, Naive Bayesian Classifier is used to get the accident severity based on Bayes rule. Then, Decision Tree classifier is used for same purpose for accident severity calculation. Finally K-Nearest Neighbour(KNN) classifier is employed for severity calculation. The accuracy of the algorithms are compared and it is found that KNN performs better than the other two algorithms employed. The major aim of the work is to find the accident severity. Also the work aims to reduce road accidents by giving awareness to public using the above method.

Sign in / Sign up

Export Citation Format

Share Document