Rokin Maharjan

Mr. Rokin Maharjan

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
13 June 2023 in Telecom
Verified
Journal Article
Open access
PDF file
RMRokin Maharjan
Rokin Maharjan
MCMd Showkat Hossain Chy
Md Showkat Hossain Chy
MAMuhammad Ashfakur Arju
Muhammad Ashfakur Arju
Tomas CernyTomas Cerny
Tomas Cerny
Message queues are a way for different software components or applications to communicate with each other asynchronously by passing messages through a shared buffer. This allows a sender to send a message without needing to wait for an immediate response from the receiver, which can help to improve the system’s performance, reduce latency, and allow components to operate independently. In this paper, we compared and evaluated the performance of four popular message queues: Redis, ActiveMQ Artemis, RabbitMQ, and Apache Kafka. The aim of this study was to provide insights into the strengths and weaknesses of each technology and to help practitioners choose the most appropriate solution for their use case. We primarily evaluated each technology in terms of latency and throughput. Our experiments were conducted using a diverse array of workloads to test the message queues under various scenarios. This enables practitioners to evaluate the performance of the systems and choose the one that best meets their needs. The results show that each technology has its own pros and cons. Specifically, Redis performed the best in terms of latency, whereas Kafka significantly outperformed the other three technologies in terms of throughput. The optimal choice depends on the specific requirements of the use case. This paper presents valuable insights for practitioners and researchers working with message queues. Furthermore, the results of our experiments are provided in JSON format as a supplement to this paper.

13 July 2025 in Future Internet
Verified
Journal Article
Open access
PDF file
RMRokin Maharjan
Rokin Maharjan
KSKorn Sooksatra
Korn Sooksatra
Tomas CernyTomas Cerny
Tomas Cerny
YRYudeep Rajbhandari
Yudeep Rajbhandari
SSSakshi Shrestha
Sakshi Shrestha
Microservice is a popular architecture for developing cloud-native applications. However, decomposing a monolithic application into microservices remains a challenging task. This complexity arises from the need to account for factors such as component dependencies, cohesive clusters, and bounded contexts. To address this challenge, we present an automated approach to decomposing monolithic applications into microservices. Our approach uses static code analysis to generate a dependency graph of the monolithic application. Then, a variational autoencoder (VAE) is used to extract features from the components of a monolithic application. Finally, the C-means algorithm is used to cluster the components into possible microservices. We evaluate our approach using a third-party benchmark comprising both monolithic and microservice implementations. Additionally, we compare its performance against two existing decomposition techniques. The results demonstrate the potential of our method as a practical tool for guiding the transition from monolithic to microservice architectures.

14 July 2025 in Future Internet
Verified
Journal Article
Open access
PDF file
YRYudeep Rajbhandari
Yudeep Rajbhandari
RMRokin Maharjan
Rokin Maharjan
SSSakshi Shrestha
Sakshi Shrestha
Tomas CernyTomas Cerny
Tomas Cerny
Software attack surfaces define the external boundaries—entry points, communication channels, and sensitive data stores through which adversaries may compromise a system. This paper introduces a scoring mechanism that produces a normalized attack-surface metric in the range of 0–1. Building on the established Damage-Potential-to-Effort ratio, our approach further incorporates real-world vulnerability intelligence drawn from MITRE’s CVE and CWE repositories. We compute each application’s score by ingesting preliminary findings from a static-analysis tool and processing them through our unified model. To assess effectiveness, we validate the scoring system across a spectrum of scenarios, from a simple Java application to complex enterprise applications. The resulting metric offers development and security teams a concise, objective measure to monitor an application’s attack surface and hence proactively identify vulnerabilities in their applications. This tool can also be used to benchmark various third-party or dependent applications, enabling both developers and security practitioners to better manage risk.

21 November 2025 in MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer
Verified
Journal Article
Open access
PDF file
HAHartono
Hartono
KKKhusnul Khotimah
Khusnul Khotimah
RMRokin Maharjan
Rokin Maharjan
Brute-force attacks remain among the most prevalent and persistent cybersecurity threats to database systems, causing unauthorized access, data leakage, and service disruptions. Conventional thresholdbased detection methods often struggle to adapt to evolving and dynamic attack patterns, necessitating more robust anomaly detection approaches. This study aims to develop, evaluate, and compare two unsupervised machine learning algorithms—Standard Isolation Forest (IF) and Rotated Isolation Forest (RIF)—for detecting brute-force attacks targeting databases such as MariaDB. A large-scale raw access log dataset containing millions of entries was pre-processed through data cleaning, normalization, and feature extraction. Behavioural features were engineered for IP-path pairs, including login-attempt frequency, request intervals, and rapid-attempt ratios. The dataset consisted of 1,831,989 benign and 5,126,052 brute-force entries. The Standard IF model was trained using benign data (n estimators = 175, contamination = 0.1, max samples = ’auto’) and evaluated on mixed data, achieving Recall 99.94%, Precision 99.29%, F1-Score 99.61%, AUC 0.9495, and Accuracy 99.28%, with TP = 5,123,224 and FN = 2,828. The RIF model, using Gaussian Random Projection (n components = 5), yielded slightly lower metrics: Recall 99.44%, F1-Score 99.36%, and Accuracy 98.81%. The findings indicate that Standard Isolation Forest provides higher detection accuracy and reliability in identifying brute-force anomalies within large-scale log data. Despite the theoretical advantage of feature rotation in handling complex anomalies, the Standard IF demonstrates superior practical performance and efficiency. Overall, the study confirms the method’s strong potential for integration into automated and real-time cybersecurity monitoring systems.