MD AL AMIN

Mr. MD AL AMIN

Information Technology, St. Francis College, Brooklyn, Connecticut, USA
orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
30 December 2024 in Journal of Technologies Information and Communication
Verified
Journal Article
Open access
PDF file
MAMD AL AMIN
MD AL AMIN
KHKamrul Hasan
Kamrul Hasan
AAAl Amin
Al Amin
SMShakik Mahmud
Shakik Mahmud
The rapid evolution of cyber threats has rendered conventional security approaches inadequate for managing increasingly sophisticated risks. This study introduces a Quantum Machine Learning Cybersecurity Framework that leverages quantum computing and machine learning to enhance cybersecurity across multiple dimensions. The research employs a structured methodology, beginning with the integration of Quantum Key Distribution (QKD) for secure key exchange and progressing through the deployment of Quantum Neural Networks (QNN) and Quantum Support Vector Machines (QSVM) for anomaly detection and adversarial threat management. The framework also incorporates Quantum Reinforcement Learning (QRL) for autonomous incident response, a Quantum Authentication module for securing identity verification using biometric and behavioral data, and a Policy Compliance Interface powered by Quantum Compliance Analyzers for regulatory adherence. Experimental results demonstrated substantial improvements in cybersecurity metrics, including a 96% accuracy in threat detection, a 28% reduction in incident response time, and a 96% success rate in compliance simulations. These findings underscore the framework's capacity to offer adaptive, scalable, and efficient cybersecurity solutions tailored to modern challenges. This study provides a significant step toward integrating quantum technologies into practical cybersecurity applications, paving the way for future innovations in intelligent, secure, and adaptable defense systems.

2 February 2026 in PLOS ONE
Verified
Journal Article
Open access
MAMD AL AMIN
MD AL AMIN
MAMohammad Shafat Ahsan
Mohammad Shafat Ahsan
JMJannatul Maua
Jannatul Maua
MAMumtahina Ahmed
Mumtahina Ahmed
Kamruddin NurKamruddin Nur
Kamruddin Nur
This paper proposes a novel Physics-Informed Self-Supervised Diagnosis (PI-SSD) framework for rotating machinery fault detection, combining physical modeling, self-supervised representation learning, and uncertainty-aware classification. The architecture integrates a multi-resolution convolutional encoder, a windowed Transformer for temporal context modeling, and a latent neural ordinary differential equation (ODE) module that embeds mechanical priors, such as Jeffcott rotor dynamics, directly into the learning process. A masked segment reconstruction objective enables self-supervised pretraining using unlabeled healthy signals, while an evidential classifier head produces fault probabilities with calibrated uncertainty. We evaluate PI-SSD on two publicly available datasets, the NASA PHM’09 Gearbox dataset and the Aalto Rotor dataset, covering 6 fault types and over 5,500 multichannel vibration recordings. Compared to seven strong baselines, PI-SSD achieves the highest Macro-F1 score (0.91) and lowest Expected Calibration Error (ECE = 0.022) on the NASA dataset, while maintaining strong domain transfer performance on Aalto (Macro-F1 = 0.81, PR-MSE = 0.067) without fine-tuning. Ablation studies confirm the contribution of each component, and physics consistency analysis demonstrates low violation rates under varying speeds. These results highlight the potential of embedding physics knowledge into self-supervised neural systems for robust, interpretable, and transferable fault diagnosis in industrial applications.

1 January 2025
Verified
Conference Paper
Open access
PDF file
ARAbdur Rahman
Abdur Rahman
MAMD AL AMIN
MD AL AMIN
SASabik Aftahee
Sabik Aftahee
MJMuhammad Junayed
Muhammad Junayed
ARAshiqur Rahman
Ashiqur Rahman
Md. Abdur Rahman, Md Al Amin, Sabik Aftahee, Muhammad Junayed, Md Ashiqur Rahman. Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025). 2025.

27 November 2025 in IEEE Open Journal of the Computer Society
Verified
Journal Article
Open access
MAMD AL AMIN
MD AL AMIN
MAMohammad Shafat Ahsan
Mohammad Shafat Ahsan
RIRahomotul Islam
Rahomotul Islam
MAMumtahina Ahmed
Mumtahina Ahmed
MMM. F. Mridha
M. F. Mridha
JHJakir Hossen
Jakir Hossen
Cloud-based systems have become prime targets for increasingly sophisticated cyberattacks due to their distributed, multi-tenant, and dynamic nature. Traditional intrusion detection systems often fail to generalize across diverse cloud environments, particularly when dealing with heterogeneous data sources such as network traffic and user behavior. In this paper, we propose a novel Dual-Encoder Adversarial Learning framework designed to detect cyber intrusions in cloud systems through a unified representation of multi-domain features. The architecture integrates private encoders for domain-specific signal extraction, a shared encoder for domain-invariant representation learning, and adversarial training implemented via a Gradient Reversal Layer to enforce cross-domain generalization. A reconstruction decoder is also employed to retain semantic fidelity in latent embeddings. Extensive experiments conducted on two benchmark datasets, UNSW-NB15 and the Cybersecurity Intrusion Detection dataset, demonstrate that the proposed model consistently outperforms state-of-the-art baselines in terms of accuracy (0.917), precision (0.903), recall (0.910), F1-score (0.906), and AUC (0.947). The model also exhibits strong robustness under noisy conditions and achieves competitive efficiency in training time and memory usage. These results validate the effectiveness of the proposed architecture for efficient and robust intrusion detection in cloud environments.

13 February 2026 in IEEE Open Journal of Intelligent Transportation Systems
Verified
Journal Article
Open access
MAMD AL AMIN
MD AL AMIN
MAMohammad Shafat Ahsan
Mohammad Shafat Ahsan
JMJannatul Maua
Jannatul Maua
AEArifa Akter Eva
Arifa Akter Eva
MMM. F. Mridha
M. F. Mridha
JHJakir Hossen
Jakir Hossen
Modern intelligent transportation systems (ITS) increasingly rely on connected electronic control units (ECUs), exposing in-vehicle networks to cyber-attacks such as message injection on the Controller Area Network (CAN) bus. While prior work has focused on post-factum detection, this paper addresses the underexplored task of forecasting cyber-attacks before they occur. We propose a spatio-temporal graph neural network (STGNN) architecture that models CAN traffic as a dynamic graph sequence, where nodes represent active CAN IDs and edges capture statistical co-activation patterns. Each graph snapshot encodes temporal features such as inter-arrival statistics and entropy, and is processed using graph attention layers followed by a multi-head temporal self-attention module. We evaluate the proposed method on two real-world datasets: Car-Hacking and OTIDS, comprising over 6.5 million labeled CAN frames from a Kia Soul under multiple attack scenarios. Experimental results show that STGNN achieves an area under the ROC curve (AUC) of 0.97, F1-score of 0.94, and a Brier score of 0.040 at a 1-second forecasting horizon on Car-Hacking, and maintains strong performance on OTIDS (AUC 0.91, F1 0.87) even though its rule-based labeling may introduce inconsistencies. The model outperforms six baseline methods across all lead times and demonstrates robustness under cross-dataset transfer and architectural variation. These findings confirm the feasibility of accurate, real-time cyberattack forecasting for automotive systems and highlight the utility of spatio-temporal graph learning for predictive cybersecurity in ITS.

26 February 2025 in International Journal of Computer Science and Information Technology
Verified
Journal Article
Closed access
MAMD AL AMIN
MD AL AMIN
As many devices connect to the internet and people save more information on the cloud and increase their usage of digital communication, the threat level on the information sphere has increased significantly. With the increase of device connectivity and use of money transactions cyber threats have become more sophisticated than ever. Conventional discrete security policies are ineffective to address the behavioral and constantly changing nature of today’s cybersecurity threats such as zero-day exploits, APTs or ransomware. In this light, AI and ML are considered strategic technologies, which define cutting-edge, intelligent, adaptive as well as scalable cybersecurity solutions. AI and ML are very effective in the processing of big data from a variety of sources including the networks traffic, logs, and endpoints behavior to detect, analyze and contain threats in real-time. In contrast, these technologies update their algorithms over time depending on new information and are therefore capable of addressing hitherto unseen vulnerabilities. Behavioral analytic system, Intrusion detection and prevention system is the most used technologies to detect, analyze and prevent cyber threats. For example, ML can pick out ‘anomalous user activity’ as a sign of insider threats or stolen login credentials while AI-based systems can stop malicious actions by analyzing network traffic in milliseconds. In addition, through AI and ML the threats are analyzed with a focus on the risk in the future based on the previous exposition. That proactive capability alone cuts response time so organizations can take more effective measures to enhance security and mitigate cyber threats to growing connectivity and increasing security on digital transactions. that organizations can do a better job of managing risk. Another way that AI helps in the incident management is making automated response mechanisms for such situations, and a system can effectively counter spontaneous threats than coming in physically. Even though they still present a number of difficulties, these technologies have certain special benefits. The use of AI by cyber adversaries by means of data poisoning attacks, algorithm shifting attack as well as adversarial AI generate new forms of risks. The criticisms regarding data privacy, bias and self-accountability of AI regarding increased cybersecurity also need to be settled. All in all, the use of AI and ML in cybersecurity is a game changer in terms of the identification, management, and prevention of threats. These technologies bring in the flexibility and wisdom to protect the current information territory from emerging threats. However, for their deployment to yield these benefits, solid frameworks should support them to reduce risk and enhance reliability. AI and ML will remain essential tools as the information sphere develops further, in order to protect the information space.