Taiwo Blessing Ogunseyi

Dr. Taiwo Blessing Ogunseyi

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
4 April 2025 in Sensors
Verified
Journal Article
Open access
PDF file
TOTaiwo Blessing Ogunseyi
Taiwo Blessing Ogunseyi
GTGogulakrishnan Thiyagarajan
Gogulakrishnan Thiyagarajan
As more IoT devices become connected to the Internet, the attack surface for cybercrimes expands, leading to significant security concerns for these devices. Existing intrusion detection systems (IDSs) designed to address these concerns often suffer from high rates of false positives and missed threats due to the presence of redundant and irrelevant information for the IDSs. Furthermore, recent IDSs that utilize artificial intelligence are often presented as black boxes, offering no explanation of their internal operations. In this study, we develop a solution to the identified challenges by presenting a deep learning-based model that adapts to new attacks by selecting only the relevant information as inputs and providing transparent internal operations for easy understanding and adoption by cybersecurity personnel. Specifically, we employ a hybrid approach using statistical methods and a metaheuristic algorithm for feature selection to identify the most relevant features and limit the overall feature set while building an LSTM-based model for intrusion detection. To this end, we utilize two publicly available datasets, NF-BoT-IoT-v2 and IoTID20, for training and testing. The results demonstrate an accuracy of 98.42% and 89.54% for the NF-BoT-IoT-v2 and IoTID20 datasets, respectively. The performance of the proposed model is compared with that of other machine learning models and existing state-of-the-art models, demonstrating superior accuracy. To explain the proposed model’s predictions and increase trust in its outcomes, we applied two explainable artificial intelligence (XAI) tools: Local Interpretable Model-agnostic Explanations (LIME) and Shapley Additive Explanations (SHAP), providing valuable insights into the model’s behavior.

6 January 2026 in Sensors
Verified
Journal Article
Open access
PDF file
TOTaiwo Blessing Ogunseyi
Taiwo Blessing Ogunseyi
GTGogulakrishnan Thiyagarajan
Gogulakrishnan Thiyagarajan
Hongang HeHongang He
Hongang He
VBVinay Bist
Vinay Bist
ZDZhengcong Du
Zhengcong Du
The opaque nature of black-box deep learning (DL) models poses significant challenges for intrusion detection systems (IDSs) in Internet of Things (IoT) networks, where transparency, trust, and operational reliability are critical. Although explainable artificial intelligence (XAI) has been increasingly adopted to enhance interpretability, its impact on detection performance and computational efficiency in resource-constrained IoT environments remains insufficiently understood. This systematic review investigates the performance of an explainable deep learning-based IDS for IoT networks by analyzing trade-offs among detection accuracy, computational overhead, and explanation quality. Following the PRISMA methodology, 129 peer-reviewed studies published between 2018 and 2025 are systematically analyzed to address key research questions related to XAI technique trade-offs, deep learning architecture performance, post-deployment XAI evaluation practices, and deployment bottlenecks. The findings reveal a pronounced imbalance in existing approaches, where high detection accuracy is often achieved at the expense of computational efficiency and rigorous explainability evaluation, limiting practical deployment on IoT edge devices. To address these gaps, this review proposes two conceptual contributions: (i) an XAI evaluation framework that standardizes post-deployment evaluation categories for explainability, and (ii) the Unified Explainable IDS Evaluation Framework (UXIEF), which models the fundamental trilemma between detection performance, resource efficiency, and explanation quality in IoT IDSs. By systematically highlighting performance–efficiency gaps, methodological shortcomings, and practical deployment challenges, this review provides a structured foundation and actionable insights for the development of trustworthy, efficient, and deployable explainable IDS solutions in IoT ecosystems.

5 June 2023 in International Journal of Information Security
Verified
Journal Article
Closed access
PDF file
TOTaiwo Blessing Ogunseyi
Taiwo Blessing Ogunseyi
Cossi Blaise AvoussoukpoCossi Blaise Avoussoukpo
Cossi Blaise Avoussoukpo
YJYiqiang Jiang
Yiqiang Jiang

6 April 2021 in IEEE Access
Verified
Journal Article
Open access
Cossi Blaise AvoussoukpoCossi Blaise Avoussoukpo
Cossi Blaise Avoussoukpo
TOTaiwo Blessing Ogunseyi
Taiwo Blessing Ogunseyi
MTMarius Tchenagnon
Marius Tchenagnon
Opportunistic Networks is a new concept that is increasingly gaining ground since it appears as a concrete example of the Internet of Things, Internet of Vehicles, Industrial Internet of Things, and the Internet of Everything with Mobile ad hoc Networks’ characteristics. An Opportunistic Network starts with a Seed OppNet that sets up the network; expands from the Seed OppNet to an extended Seed OppNet through devices’ discovery. The characteristics of Opportunistic Networks make OppNets more challenging than any other networks. So, a deep understanding of OppNets’ characteristics and demands is an unavoidable precondition before proposing any OppNets related scheme. However, under OppNets’ constraints, the relevance of the Opportunistic Networks related articles in literature is yet to be established. Also, most surveys tackling Opportunistic Networks do not give a complete insight into what Opportunistic Networks stand for. This work reviews state of the art on Opportunistic Networks providing three main contributions. First, resorting to the primary definition of Opportunistic Networks, it elucidates what OppNets are, pointing out the particularities of an OppNet, its domains of applications, and challenges. Second, it provides a comprehensive review that encompasses most Opportunistic Networks’ research areas: routing, intrusion detection, authentication, privacy protection, data aggregation, and the technology for OppNets, organising them in a taxonomy. Third, it evaluates the role of the Seed OppNet in Opportunistic Networks related schemes. Any proposed OppNets related scheme, to be relevant to OppNets’ research, should include OppNets’ characteristics and demands.

15 December 2023 in IEEE Access
Verified
Journal Article
Open access
TOTaiwo Blessing Ogunseyi
Taiwo Blessing Ogunseyi
OAOluwasola Mary Adedayo
Oluwasola Mary Adedayo
The acquisition and analysis of data in digital forensics raise different data privacy challenges. Many existing works on digital forensic readiness discuss what information should be stored and how to collect relevant data to facilitate investigations. However, the cost of this readiness often directly impacts the privacy of innocent third parties and suspects if the collected information is irrelevant. Approaches that have been suggested for privacy-preserving digital forensics focus on the use of policy, non-cryptography-based, and cryptography-based solutions. Cryptographic techniques have been proposed to address issues of data privacy during data analysis. As the utilization of some of these cryptographic techniques continues to increase, it is important to evaluate their applicability and challenges in relation to digital forensics processes. This study provides digital forensics investigators and researchers with a roadmap to understanding the data privacy challenges in digital forensics and examines the various privacy techniques that can be utilized to tackle these challenges. Specifically, we review the cryptographic techniques applied for privacy protection in digital forensics and categorize them within the context of whether they support trusted third parties, multiple investigators, and multi-keyword searches. We highlight some of the drawbacks of utilizing cryptography-based methods in privacy-preserving digital forensics and suggest potential solutions to the identified shortcomings. In addition, we propose a conceptual privacy-preserving digital forensics (PPDF) model that is based on the use of cryptographic techniques and analyze the model within the context of the above-mentioned factors. An evaluation of the model is provided through a consideration of identified factors that may affect an investigation. Lastly, we provide an analysis of how existing principles for preserving privacy in digital forensics are addressed in our PPDF model. Our evaluation shows that the model aligns with many of the existing privacy principles recommended for privacy protection in digital forensics.

22 June 2021 in IEEE Access
Verified
Journal Article
Open access
TOTaiwo Blessing Ogunseyi
Taiwo Blessing Ogunseyi
Cossi Blaise AvoussoukpoCossi Blaise Avoussoukpo
Cossi Blaise Avoussoukpo
YJYiqiang Jiang
Yiqiang Jiang
Cross-domain recommender systems are known to provide solutions to the cold start and data sparsity problems in recommender systems. This can be achieved by leveraging sufficient ratings and users' profiles in one domain to enhance accurate recommendations in another domain. However, domains with sufficient ratings are not willing to share their users' ratings with other recommender systems or domains due to users' privacy and legal concern. Hence this shows a need for a privacy-preserving mechanism that encourages secure knowledge transfer between different domains. This study proposes a privacy-preserving cross-domain recommender system based on matrix factorization. Specifically, the study formally described the privacy requirements of a cross-domain recommender system, which are different from a single domain recommender system. It designs a new framework for a privacy-preserving cross-domain recommender system and then utilized the somewhat homomorphic encryption (SWHE) scheme to ensure users' privacy. The SWHE scheme was used to encrypt users' ratings in different domains, shared latent factor approach was implemented between the domains and extracted knowledge was securely transferred from the source domain to the target domain. We prove that users' privacy is secured throughout the stages involved in the proposed protocol. Experiments on both synthetic and real datasets demonstrate the efficiency of our protocol.