Rangamati Science and Technology University

About: Rangamati Science and Technology University is a education organization based out in Chittagong, Bangladesh. It is known for research contribution in the topics: Feature extraction & Deep learning. The organization has 26 authors who have published 41 publications receiving 111 citations.

Phishing Attacks Detection using Machine Learning Approach

Abstract: Evolving digital transformation has exacerbated cybersecurity threats globally. Digitization expands the doors wider to cybercriminals. Initially cyberthreats approach in the form of phishing to steal the confidential user credentials. Usually, Hackers will influence the users through phishing in order to gain access to the organizatlou's digital assets and networks. With security breaches, cybercriminals execute ransomware attack, get unauthorized access, and shut down systems and even demand a ransom for releasing the access. Anti-phishing software and techniques are circumvented by the phishers for dodging tactics. Though threat intelligence and behavioural analytics systems support organizations to spot the unusual traffic patterns, still the best practice to prevent phishing attacks is defended in depth. In this perspective, the proposed research work has developed a model to detect the phishing attacks using machine learning (ML) algorithms like random forest (RF) and decision tree (DT). A standard legitimate dataset of phishing attacks from Kaggle was aided for ML processing. To analyze the attributes of the dataset, the proposed model has used feature selection algorithms like principal component analysis (PCA). Finally, a maximum accuracy of 97% was achieved through the random forest algorithm.

Phishing Attacks Detection using Deep Learning Approach

Abstract: In the COVID-19 pandemic, people are enforced to adopt ‘work from home’ policy. The Internet has become an effective channel for social interactions nowadays. Peoples' immense dependence on digital platform opens doors for fraud. Phishing is a type of cybercrime to steal users' credentials from online platforms such as online banking, online business, e-commerce, online classroom, digital marketplaces, etc. Phishers develop fake webpages alike the original one and send spam emails to hook the users. Phishers seize users' credentials when an online user visits the counterfeit webpages through the spams. Researchers have introduced enormous tools like blacklist, white-list, and antivirus software to detect phishing webpages. Attackers always devise creative ways to exploit human and network weakness to penetrate cyber defense. This paper presents a data-driven framework for detecting phishing webpages using deep learning approach. More precisely, a multilayer perceptron, which is also referred as a feed-forward neural network is used to predict the phishing webpages. The dataset was collected from Kaggle and contains information of ten thousand webpages. It consists of ten attributes. The proposed model has achieved 95% training accuracy and 93% test accuracy.

Performance analysis of a surveillance system to detect and track vehicles using Haar cascaded classifiers and optical flow method

Abstract: This paper presents the real time vehicle detection and tracking system, based on data, collected from a single camera In this system, vehicles are detected by using Haar Feature-based Cascaded Classifier on static images, extracted from the video file The advantage of this classifier is that, it uses floating numbers in computations and hence, 20% more accuracy can be achieved in comparison to other classifiers and features of classifiers such as LBP (Local Binary Pattern) Tracking of the vehicles is carried out using Lucas-Kanade and Horn Schunk Optical Flow method because it performs better than other methods such as Morphological and Correlation Transformations The proposed system consists of vehicle detection and tracking; and it is evaluated by using real data, collected from the route networks of Chittagong City of Bangladesh

Bank Fraud Detection using Community Detection Algorithm

Abstract: Bank fraud is a federal crime that involves fraudulent attempts aims for monetary gains by deceiving financial institutions. Every year, banks and financial institutions lose billions due to fraud. Fraudsters tempt bankers through scams to gain financial assets. The most common types of bank fraud include debit and credit card fraud, account fraud, insurance fraud, money laundering fraud, etc. Bankers are obliged to safeguard their financial assets as well as institutional integrity to armored the global financial system. Anti-fraud guard systems are regularly circumvented by fraudsters' dodging techniques. This paper proposed a system to detect bank fraud using a community detection algorithm that identifies the patterns that can lead to fraud occurrences. An agile method was used to design the web-based application to detect the fraud. The application functioned as a central hub between the banks and customers. Neo4j, a graph database, was used for creating and representing the database, and the Cypher query was used as a graph query language. The proposed system successfully detected all frauds presented during the test experiment. This paper will assist bankers to combat fraud by detecting and preventing similar occurrences.