A Novel Approach for Malicious URL Detection Based on the Joint Model

The number of malicious websites is increasing yearly, and many companies and individuals worldwide have suffered losses. Therefore, the detection of malicious websites is a task that needs continuous development. In this study, a joint neural network algorithm model combining the attention mechanism, bidirectional independent recurrent neural network (Bi-IndRNN), and capsule network (CapsNet) is proposed. The word vector tool word2vec trains the character- and word-level uniform resource locator (URL) static embedding vector features. At the same time, the algorithm will also extract texture fingerprint features that can compare the content differences of different malicious web URL binary files. Then, the extracted features are fused and input into the joint neural network algorithm model. First, the multihead attention mechanism is used to extract contextual semantic features by adjusting weights and Bi-IndRNN. Second, CapsNet with dynamic routing is used to extract deep semantic information. Finally, the sigmoid classifier is used for classification. This study uses different methods from different angles to extract more comprehensive features. From the experimental results, the method proposed in this study improves the classification accuracy of malicious web page detection compared with other researchers.

Click Fraud Detection Approaches to analyze the Ad Clicks Performed by Malicious Code

Mobile PR is an important component of the mobile app ecosystem. A major threat to this ecosystem’s long-term health is click fraud, which involves clicking on ads while infected with malware or using an automated bot to do it for you. The methods used to identify click fraud now focus on looking at server requests. Although these methods have the potential to produce huge numbers of false negatives, they may easily be avoided if clicks are hidden behind proxies or distributed globally. AdSherlock is a customer-side (inside the app) efficient and deployable click fraud detection system for mobile applications that we provide in this work. AdSherlock separates the computationally expensive click request identification procedures into an offline and online approach. AdSherlock uses URL (Uniform Resource Locator) tokenization in the Offline phase to create accurate and probabilistic patterns. These models are used to identify click requests online, and an ad request tree model is used to detect click fraud after that. In order to develop and evaluate the AdSherlock prototype, we utilise actual applications. It injects the online detector directly into an executable software package using binary instrumentation technology (BIT). The findings show that AdSherlock outperforms current state-of-the-art methods for detecting click fraud with little false positives. Advertisement requests identification, mobile advertising fraud detection are some of the keywords used in this article.

Feature based Phishing Website Detection using Random Forest Classifier

In today’s world, one of the most vulnerable security threat which poses a problem to the internet users is phishing. Phishing is an attack made to steal the sensitive information of the users such as password, PIN, card details etc., In a phishing attack, the attacker creates a fake website to make the users click it and steal the sensitive information of users. . In this paper, we propose a feature-based phishing detection technique that uses uniform resource locator (URL) features. This paper focuses on the extracting the features which are then classified based on their effect within a website. The feature groups include address- bar related features, abnormal- based features, HTML – JavaScript based features and domain based features. We plan to use machine learning and implement some classification algorithms and compare the performance of these algorithms on our dataset.

Opinions of Investors on Nepal Stock Exchange Limited (NEPSE) Online Trading System

Nepal Stock Exchange Limited (NEPSE) is only a secondary market in Nepal. After almost three decades of its establishment, the NEPSE trading system turned fully automated on January 17, 2021. The new system is named NEPSE Online Trading System (NOTS), which was launched on November 6, 2018. After the breakout of the COVID-19, the NOTS users using NEPSE online Trade Management System (TMS) and Uniform Resource Locator (URL) increased due to the nation-wide lockdown as well as the compulsion from the governing body. Hence, the paper attempts to get opinions from the NOTS users about its features and performance. The paper has taken 300 NOTS users as samples for the survey purpose. The online survey was conducted for the study. A 5–points Likert scale-based questionnaire was forwarded to the potential online traders (investors) through an online platform such as messenger and email. The study has followed descriptive statistics and a one-sample t-test to interpret the collected data from the NOTS users. The study found that there is an issue of the market data display in the NOTS platform, which needs to be addressed as soon as possible. At the same time, the respondents stated that the best parts of NOTS were that it has helped them to specify and customize the securities, price, and volume that one would like to trade on a real-time basis.

Detecting Phishing Website Using Machine Learning

A fraud attempt to get sensitive and personal information like password, username, and bank details like credit/debit card details by masking as a reliable organization in electronic communication. The phishing website will appear the same as the legitimate website and directs the user to a page to enter personal details of the user on the fake website. Through machine learning algorithms one can improve the accuracy of the prediction. The proposed method predicts the URL based phishing websites based on features and also gives maximum accuracy. This method uses uniform resource locator (URL) features. We identified features that phishing site URLs contain. The proposed method employs those features for phishing detection. The proposed system predicts the URL based phishing websites with maximum accuracy.

A Comparative Analysis of Search Engine Ranking Algorithms

Ranking Algorithm is the most proper way of positioning on a scale. As the information and knowledge on the internet are increasing every day.The search engine's ability to deliver the most appropriate material to the customer. It is more and more challenging without even any assistance in filtering through all of it. However, searching what user requires is extremely difficult. In this research, an effort has been made to compare and analyze the most popular and effective search engines. The keywords were used in uniform resource locator like, title tag, header, or even the keyword's resembles to the actual text. The page rank algorithm computes a perfect judgment of how relevant a webpage is by analyzing the quality and calculating the number of links connected to it. In this study the keyword relevancy and time response were used for search engines and observed the results. It is observed that the google search engine is faster than the bing and youtube, and after all, bing is the best search engine after google. Moreover, youtube is the fastest search engine in terms of video content search. The google results were found more accurate. However, it is better than all of the search engine

Game Hafalan Ayat Al-Qur’an Berbasis Android Bagi Siswa Sekolah Dasar Islam Terpadu

Pendidikan karakter semenjak usia dini merupakan program yang sedang digalakkan oleh pemerintah. Untuk menjawab tantangan itu, SD IT Al Mansyur yang terdapat di Desa Balunijuk, Kabupaten Bangka, menyelenggarakan pendidikan formal yang berbasis ilmu pengetahuan, iman dan takwa. Proses pembelajaran di SD IT Al Mansyur masih bersifat klasikal. Kesulitan yang sering ditemui siswa adalah sulitnya siswa menghafal ayat-ayat Al-Qur’an karena suasana pembelajaran yang terkesan formal dalam bentuk hafalan. Untuk itu, pada penelitian ini dikembangkan game berbasis Android untuk mempermudah hafalan ayat Al-Qur’an bagi siswa. Game hafalan dirancang dan dibangun menggunakan metode Waterfall dan menggunakan Uniform Resource Locator (URL) untuk mengambil data suara ke Dropbox service. Penelitian ini menghasilkan game hafalan yang telah memiliki fitur-fitur hafalan untuk menghafal Al-Qur’an di SD IT Al Mansyur.

A Supplementary Tool for Web-archiving Using Blockchain Technology

The usefulness of a uniform resource locator (URL) on the World Wide Web is reliant on the resource being hosted at the same URL in perpetuity. When URLs are altered or removed, this results in the resource, such as an image or document, being inaccessible. While web-archiving projects seek to prevent such a loss of online resources, providing complete backups of the web remains a formidable challenge. This article outlines the initial development and testing of a decentralised application (DApp), provisionally named Repudiation Chain, as a potential tool to help address these challenges presented by shifting URLs and uncertain web-archiving. Repudiation Chain seeks to make use of a blockchain smart contract mechanism in order to allow individual users to contribute to web-archiving. Repudiation Chain aims to offer unalterable assurance that a specific file and its URL existed at a given point in time—by generating a compact, non-reversible representation of the file at the time of its non-repudiation. If widely adopted, such a tool could contribute to decentralisation and democratisation of web-archiving.