Geo Francis Edakulathur

Dr. Geo Francis Edakulathur

Computer Science, Karpagam Academy of Higher Education, Coimbatore, India
orcid
HSST Jr., St. Aloysius H.S.S., Elthuruth, Thrissur, India

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
15 December 2022
Verified
Conference Paper
Closed access
Geo Francis EdakulathurGeo Francis Edakulathur
Geo Francis Edakulathur
SSS Sheeja
S Sheeja
With the growth of the number in smart devices based on IoT, keeping a secure data processing among them has become even more significant in cloud computing. However, a high security is needed to protect the huge amount of data privacy. In this regard, many authentication approaches are presented in IoT-Cloud-based Architecture. However, computation, latency, and security strength are major issues to provide authentication for users. We propose the Multifactor Scalable Lightweight Cryptography for IoT-Cloud to enhance security to protect the user or organization's information. The non-sensitive and sensitive data are generated from IoT devices and stored in our proposed hybrid public and private cloud after the encryptions. Hence, encryptions for public cloud and private cloud data are done by Digital Signature Algorithm and Policy based Attribute encryption algorithm with Moth fly optimization. This optimization is chosen as the key parameter efficiently. The three multifactors are then used to perform the three levels of authentication by Trust based Authentication Scheme. Following this, the proposed multifactor authentication is simulated and compared with existing approaches to analyze the performance in terms of computational and execution time and security strength. As a result, the proposed method is shown 97% of security strength and minimum computation and execution time than other conventional approaches.

1 September 2024 in Journal of Multiscale Modelling
Verified
Journal Article
Closed access
Geo Francis EdakulathurGeo Francis Edakulathur
Geo Francis Edakulathur
SSS. Sheeja
S. Sheeja
EJE. F. Antony John
E. F. Antony John
JJJismy Joseph
Jismy Joseph


24 January 2024 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
Geo Francis EdakulathurGeo Francis Edakulathur
Geo Francis Edakulathur
SSSheeja S
Sheeja S

28 December 2022
Verified
Conference Paper
Closed access
Geo Francis EdakulathurGeo Francis Edakulathur
Geo Francis Edakulathur
SSS Sheeja
S Sheeja
Wireless Sensor Networks (WSN), which collect a large amount of confidential data related to the activities of the user, have emerged as a promising research platform recently. The main purpose of ambient intelligence might be easily damaged by an attacker tampering with those kinds of data. Hence, it is significant to secure the data. In the existing intrusion detection techniques, due to single-time authentication, the robustness level is low; thus, if any high-level attack occurs, there is a chance of skipping them. So, a novel R-Distributed Auto-Encoder (RDAE)-based Pseudo Random number based Quantum Key Distribution (PSR-QKD) is employed for energy-efficient intrusion detection to overcome the limitations. Initially, the node initialization is done and the original ID is assigned to them. By employing K-Nearest Neighbour (KNN) algorithm, the clustering is performed. Then, by deploying Double Precision Integrated-Golden Tortoise Beetle Optimizer (DPI-GTBO), the cluster heads are selected. For acquiring the unique ID, the original ID of the CH is hashed by RIPE Message Digest (RIPEMD)-128. By using the PSR-QKD technique, key generation is performed in the server. The Base Station (BS) verifies the node based on trust value and shares the public key during a new node entry. By employing RDAE, the CH matches the public key with the server and performs attack detection. In the end, CH shares the private key with the non-malicious nodes. When analogized to the prevailing methodologies, the proposed method is found to be more efficient.

6 April 2024
Verified
Conference Paper
Closed access
Geo Francis EdakulathurGeo Francis Edakulathur
Geo Francis Edakulathur
SSS. Sheeja
S. Sheeja
EJE.F. Antony John
E.F. Antony John
JJJismy Joseph
Jismy Joseph
The rapid proliferation of Internet of Things (IoT) devices has revolutionized various domains, introducing unprecedented convenience and efficiency. However, this expansion has concurrently intensified the obstacles associated with network security. Detecting and mitigating anomalies in IoT networks are of utmost importance to protect critical systems and sensitive data. This paper presents an innovative approach to IoT network security that combines Principal Component Analysis (PCA) with advanced deep learning approaches, encompassing Generative Adversarial Networks (GANs) and Transformers. In this research, we investigate the potential of PCA for dimensionality reduction and feature selection within IoT network data. By simplifying data complexity, PCA aids in uncovering critical features and patterns contributing to network anomalies. Advanced deep learning models, such as GANs for generating synthetic data and Transformers for sequence modeling, are harnessed to construct anomaly detection systems capable of identifying irregularities in real-time IoT data streams. Our approach is rigorously evaluated on a comprehensive dataset collected from diverse IoT devices and networks. The results underscore the efficacy of the PCA and deep learning-based anomaly detection model, leveraging GANs and Transformers, in accurately and efficiently unmasking anomalies in IoT network traffic. Through extensive experiments and evaluations, we underscore substantial advancements over traditional security methods. This research significantly enhances IoT network security by presenting a sophisticated, data-driven anomaly detection system adaptable to the dynamic and evolving nature of IoT environments. As the IoT landscape continues to expand, our approach offers a crucial solution to safeguard against the ever-evolving threat of network anomalies.