Browsing by Author "Azeez, Nureni Ayofe"

Now showing 1 - 4 of 4

Citation - WoS: 31
Citation - Scopus: 54
Adopting Automated Whitelist Approach for Detecting Phishing Attacks
(Elsevier Advanced Technology, 2021) Azeez, Nureni Ayofe; Misra, Sanjay; Margaret, Ihotu Agbo; Fernandez-Sanz, Luis; Abdulhamid, Shafi'i Muhammad; Computer Engineering
Phishing is considered a great scourge in cyberspace. Presently, there are two major challenges known with the existing anti-phishing solutions. Low detection rate and lack of quick access time in a real-time environment. However, it has been established that blacklist solution methods offer quick and immediate access time but with a low detection rate. This research paper presents an automated white-list approach for detecting phishing attacks. The white-list is determined by carrying out a detailed analysis between the visual link and the actual link. The similarities of the known trusted site are calculated by juxtaposing the domain name with the contents of the whitelist and later match it with the IP address before a decision is made and further analyzing the actual link and the visual link by calculating the similarities of the known trusted site. The technique then takes a final decision on the extracted information from the hyperlink, which can also be obtained from the web address provided by the user. The experiments carried out provided a very high level of accuracy, specifically, when the dataset was relatively at the lowest level. Six different datasets were used to perform the experiments. The average accuracy obtained after the six experiments was 96.17% and the approach detects phishing sites with a 95.0% true positive rate. It was observed that the level of accuracy varies from one dataset to another. This result shows that the proposed method performs better than similar approaches benchmarked with. The efficiency of the approach was further established through its computation time, memory, bandwidth as well as other computational resources that were utilized with the minimum requirements when compared with other approaches. This solution has provided immense benefits over the existing solutions by reducing the memory requirements and computational complexity, among other benefits. It has also shown that the proposed method can provide more robust detection performances when compared to other techniques. (c) 2021 Elsevier Ltd. All rights reserved.
Citation - WoS: 24
Identifying Phishing Attacks in Communication Networks Using Url Consistency Features
(inderscience Enterprises Ltd, 2020) Azeez, Nureni Ayofe; Salaudeen, Balikis Bolanle; Misra, Sanjay; Damasevicius, Robertas; Maskeliunas, Rytis; Computer Engineering
Phishing is a fraudulent attempt by cybercriminals, where the target audience is addressed by a text message, phone call or e-mail, requesting classified and sensitive information after presenting himself/herself as a legitimate agent. Successful phishing attack may result into financial loss and identity theft. Identifying forensic characteristics of phishing attack can help to detect the attack and its perpetuators and as well as to enable defence against it. To shield internet users from phishing assaults, numerous anti-phishing models have been proposed. Currently employed techniques to handle these challenges are not sufficient and capable enough. We aim at identifying phishing sites in order to guard internet users from being vulnerable to any form of phishing attacks by verifying the conceptual and literal consistency between the uniform resource locator (URL) and the web content. The implementation of the proposed PhishDetect method achieves an accuracy of 99.1%; indicating that it is effective in detecting various forms of phishing attacks.
Citation - WoS: 24
Citation - Scopus: 39
Network Intrusion Detection With a Hashing Based Apriori Algorithm Using Hadoop Mapreduce
(Mdpi, 2019) Azeez, Nureni Ayofe; Ayemobola, Tolulope Jide; Misra, Sanjay; Maskeliunas, Rytis; Damasevicius, Robertas; Computer Engineering
Ubiquitous nature of Internet services across the globe has undoubtedly expanded the strategies and operational mode being used by cybercriminals to perpetrate their unlawful activities through intrusion on various networks. Network intrusion has led to many global financial loses and privacy problems for Internet users across the globe. In order to safeguard the network and to prevent Internet users from being the regular victims of cyber-criminal activities, new solutions are needed. This research proposes solution for intrusion detection by using the improved hashing-based Apriori algorithm implemented on Hadoop MapReduce framework; capable of using association rules in mining algorithm for identifying and detecting network intrusions. We used the KDD dataset to evaluate the effectiveness and reliability of the solution. Our results obtained show that this approach provides a reliable and effective means of detecting network intrusion.
Citation - WoS: 51
Citation - Scopus: 93
Windows Pe Malware Detection Using Ensemble Learning
(Mdpi, 2021) Azeez, Nureni Ayofe; Odufuwa, Oluwanifise Ebunoluwa; Misra, Sanjay; Oluranti, Jonathan; Damasevicius, Robertas; Computer Engineering
In this Internet age, there are increasingly many threats to the security and safety of users daily. One of such threats is malicious software otherwise known as malware (ransomware, Trojans, viruses, etc.). The effect of this threat can lead to loss or malicious replacement of important information (such as bank account details, etc.). Malware creators have been able to bypass traditional methods of malware detection, which can be time-consuming and unreliable for unknown malware. This motivates the need for intelligent ways to detect malware, especially new malware which have not been evaluated or studied before. Machine learning provides an intelligent way to detect malware and comprises two stages: feature extraction and classification. This study suggests an ensemble learning-based method for malware detection. The base stage classification is done by a stacked ensemble of fully-connected and one-dimensional convolutional neural networks (CNNs), whereas the end-stage classification is done by a machine learning algorithm. For a meta-learner, we analyzed and compared 15 machine learning classifiers. For comparison, five machine learning algorithms were used: naive Bayes, decision tree, random forest, gradient boosting, and AdaBoosting. The results of experiments made on the Windows Portable Executable (PE) malware dataset are presented. The best results were obtained by an ensemble of seven neural networks and the ExtraTrees classifier as a final-stage classifier.