Edward Kwadwo Boahen

Dr. Edward Kwadwo Boahen

Ghana Communication Technology University, Accra, Greater Accra, Ghana
+1
orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 May 2021 in Computers & Security
Verified
Journal Article
Closed access
Edward Kwadwo BoahenEdward Kwadwo Boahen
Edward Kwadwo Boahen
Brunel Elvire BOUYA-MOKOBrunel Elvire BOUYA-MOKO
Brunel Elvire BOUYA-MOKO
CWChangda Wang
Changda Wang

2 September 2022 in IEEE Transactions on Computational Social Systems
Verified
Journal Article
Closed access
Edward Kwadwo BoahenEdward Kwadwo Boahen
Edward Kwadwo Boahen
Brunel Elvire BOUYA-MOKOBrunel Elvire BOUYA-MOKO
Brunel Elvire BOUYA-MOKO
Faizan QamarFaizan Qamar
Faizan Qamar
CWChangda Wang
Changda Wang
The major threat to online social network (OSN) users is account compromisation. Spammers now spread malicious messages by exploiting the trust relationship established between account owners and their friends. The challenge in detecting a compromised account by service providers is validating the trusted relationship established between the account owners, their friends, and the spammers. Another challenge is the increase in required human interaction with feature selection. Research available on supervised learning has limitations with feature selection and accounts that cannot be profiled, like application programming interface (API). Therefore, this article discusses the various behaviors of OSN users and the current approaches in detecting a compromised OSN account, emphasizing its limitations and challenges. We propose a deep learning approach that addresses and resolve the constraints faced by previous schemes. We detailed our proposed optimized nonsymmetric deep autoencoder (OPT $\_$ NSDAE) for unsupervised feature learning, which reduces the required human interaction levels in the selection and extraction of features. We evaluated our proposed classifier using three different social network datasets, Facebook, Google $+$ , and Twitter, in addition to the NSL-KDD and KDDCUP’99 datasets, in a graphical-user-interface-enabled Weka application. The experimental results show that our proposed approach outperformed most of the traditional schemes in OSN compromised account detection.

29 June 2020 in Applied Artificial Intelligence
Verified
Journal Article
Closed access
Edward Kwadwo BoahenEdward Kwadwo Boahen
Edward Kwadwo Boahen
CWChangda Wang
Changda Wang
Brunel Elvire BOUYA-MOKOBrunel Elvire BOUYA-MOKO
Brunel Elvire BOUYA-MOKO
The primary threat to online social network (OSN) users is account compromisation. The challenge in detecting a compromised account is due to the trusted relationship established between the account owners, their friends, and the service providers. The available research which focuses on using machine learning has limitations with human experts involved in feature selection and a standardized dataset. The paper discusses users` various behaviors of users of OSN and the up-to-date approaches in detecting a compromised OSN account with emphasis on the limitations and challenges. Furthermore, we propose an enhanced machine learning approach Word Embedding and KNN (WE-KNN), which addresses the limitations faced by the previous techniques used. We detailed our proposed WE-KNN for feature extraction, selection of behavior of OSN users, and classification. Our proposed model is evaluated using the standard benchmark datasets, namely KDD Cup ‘99 and NSL-KDD and implemented it in WEKA. Besides, we used state-of-the-art evaluation metrics to assess the performance of our model. The results obtained depicts that the proposed approach in compromise account detection performs better.

1 November 2024 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
Edward Kwadwo BoahenEdward Kwadwo Boahen
Edward Kwadwo Boahen
RSRexford Nii Ayitey Sosu
Rexford Nii Ayitey Sosu
SOSelasi Kwame Ocansey
Selasi Kwame Ocansey
QXQinbao Xu
Qinbao Xu
CWChangda Wang
Changda Wang
Online Social Networks (OSNs) face escalating security threats that imperil user privacy. Conventional Deep Learning methods, relying predominantly on fixed learning rates, encounter limitations when capturing the nuanced intricacies of OSN traffic that arise from shifting user behaviors, diverse content types, and evolving interaction patterns because of social trending topics changes. To tackle these challenges, our paper delves into the diverse variations and transitions from a uniform approach, where a single method is employed for various types of data, to a multi-variation methodology. This methodology dynamically adapts to the special characteristics of each data type, resulting in more effective data representation while alleviating the limitations associated with fixed-rate calibration. Therefore, we devise the Adaptive Swarm Reinforcement Learning (ASRL) method that leverages adaptive learning to intricately analyze a wide range of user interactions, endowing our proposed method with the capacity to flexibly adjust to the constantly shifting OSN patterns. The experiments show that the proposed ASRL method achieves an accuracy of 98.59% in detecting a range of threat patterns, surpassing other prevalent methods by an average of 5% across the datasets from Facebook, Google+, and Twitter. Meanwhile, ASRL logs suspicious activities to identify the intruder for forensic analysis. The implementation of our proposed method is now publicly accessible at https://github.com/don2c/asrl_Project.

25 May 2022 in Electronics
Verified
Journal Article
Open access
PDF file
Brunel Elvire BOUYA-MOKOBrunel Elvire BOUYA-MOKO
Brunel Elvire BOUYA-MOKO
Edward Kwadwo BoahenEdward Kwadwo Boahen
Edward Kwadwo Boahen
CWChangda Wang
Changda Wang
Strong network connections make the risk of malicious activities emerge faster while dealing with big data. An intrusion detection system (IDS) can be utilized for alerting suitable entities when hazardous actions are occurring. Most of the techniques used to classify intrusions lack the techniques executed with big data. This paper devised an optimization-driven deep learning technique for detecting the intrusion using the Spark model. The input data is fed to the data partitioning phase wherein the partitioning of data is done using the proposed fuzzy local information and Bhattacharya-based C-means (FLIBCM). The proposed FLIBCM was devised by combining Bhattacharya distance and fuzzy local information C-Means (FLICM). The feature selection was achieved with classwise info gained to select imperative features. The data augmentation was done with oversampling to make it apposite for further processing. The detection of intrusion was done using a deep Maxout network (DMN), which was trained using the proposed student psychology water cycle caviar (SPWCC) obtained by combining the water cycle algorithm (WCA), the conditional autoregressive value at risk by regression quantiles (CAViaR), and the student psychology-based optimization algorithm (SPBO). The proposed SPWCC-based DMN offered enhanced performance with the highest accuracy of 97.6%, sensitivity of 98%, and specificity of 97%.

1 January 2023 in IET Software
Verified
Journal Article
Open access
PDF file
RSRexford Nii Ayitey Sosu
Rexford Nii Ayitey Sosu
Jinfu ChenJinfu Chen
Jinfu Chen
Edward Kwadwo BoahenEdward Kwadwo Boahen
Edward Kwadwo Boahen
ZZZikang Zhang
Zikang Zhang
Smart contracts have gained immense popularity in recent years as self‐executing programs that operate on a blockchain. However, they are not immune to security flaws, which can result in significant financial losses. These flaws can be detected using dynamic analysis methods that extract various aspects from smart contract bytecode. Methods currently used for identifying vulnerabilities in smart contracts mostly rely on static analysis methods that search for predefined vulnerability patterns. However, these patterns often fail to capture complex vulnerabilities, leading to a high rate of false negatives. To overcome this limitation, researchers have explored machine learning‐based methods. However, the accurate interpretation of complex logic and structural information in smart contract code remains a challenge. In this study, we present a technique that combines real‐time runtime batch normalization and data augmentation for data preprocessing, along with n‐grams and one‐hot encoding for feature extraction of opcode sequence information from the bytecode. We then combined bidirectional long short‐term memory (BiLSTM), convolutional neural network, and the attention mechanism for vulnerability detection and classification. Additionally, our model includes a gated recurrent units memory module that enhances efficiency using historical execution data from the contract. Our results demonstrate that our proposed model effectively identifies smart contract vulnerabilities.