Papers by Nalini Subramanian
Concurrency and Computation: Practice and Experience, 2018
Security is one of the important challenges faced by cloud computing. There are so many methods l... more Security is one of the important challenges faced by cloud computing. There are so many methods like encryption, firewall, and providing access control to achieve security. These methods alone cannot provide a flawless access to the available resources. We are in need of a paradigm that permits only authenticated users to access the resources from the cloud. The objective of the proposed paradigm is to provide a strong authentication. Our proposed method considers only the appropriate parameters from the available plenty of parameters, which is used to prove a user to be an authenticated person. The selection of the required parameters is achieved using Principle Component Analysis, then Support Vector Machine classifies accurately the authenticated and unauthenticated users. The simulation result shows that our proposed paradigm achieves high security. We compute our paradigm with various evaluation metrics and we compared with similar models like Support Vector Machine and Artificial Neural Networks. We got great improvement. In order to reduce the complexity, the number of parameters is reduced because, if the parameters are huge, the algorithm prediction will be more complex, which leads to false negatives.
Multivariate Classification of Dry Beans using Pipelined Dimensionality Reduction Technique
2022 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)
International journal of health sciences
The proposed effort has the purpose of predicting an individuals insurance expenses also identif... more The proposed effort has the purpose of predicting an individuals insurance expenses also identifying people having medical insurance plans and clinical data, irrespective of their health concerns. A patient will require many types of health insurance. Regardless of the type of insurance coverage a person has, it is feasible to estimate their health insurance expenditures depends on the degree of critical care they get. The random forest Regression is one of the regressors used in this investigation. When the accuracies were compared, hyper parameter tuning was the most effective of all the approaches, with a 98 percent accuracy. Finally, the prediction fit will calculate the insurance expense of the user and calculate the insurance costs.
Blockchain based Medical Record Storage and Retrieval using NFT Tracking System
2022 6th International Conference on Trends in Electronics and Informatics (ICOEI)
Smart Video Survillance Based Weapon Identification Using Yolov5
2022 International Conference on Electronic Systems and Intelligent Computing (ICESIC)
A way to explore SMS: Social Media Scams for a secure Digi-world
2021 5th International Conference on Electronics, Communication and Aerospace Technology (ICECA), 2021
Social media is a revolutionary phenomenon, which deals with how consumers look for information, ... more Social media is a revolutionary phenomenon, which deals with how consumers look for information, interact with their work and communicate with one another. There are billions of active users in various social medias like Twitter, WhatsApp, Facebook and Instagram with numbers that go up to one million every day. This provides way for criminals to use a wide range of tactics to connect and commit fraud. Constantly using innovative ways to access the personal data is achieved by Scammers. Social media scams degrade the trust of consumers. This paper focuses on scams and provides different ways to various agencies to improve safety and minimize harmful damages. It helps in upgrading the consumer awareness on social media scams which is the heart and soul for a secure Digi-world.
Supervised malware learning in cloud through System calls analysis
2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), 2021
Even if there is a rapid proliferation with the advantages of low cost, the emerging on-demand cl... more Even if there is a rapid proliferation with the advantages of low cost, the emerging on-demand cloud services have led to an increase in cybercrime activities. Cyber criminals are utilizing cloud services through its distributed nature of infrastructure and create a lot of challenges to detect and investigate the incidents by the security personnel. The tracing of command flow forms a clue for the detection of malicious activity occurring in the system through System Calls Analysis (SCA). As machine learning based approaches are known to automate the work in detecting malwares, simple Support Vector Machine (SVM) based approaches are often reporting low value of accuracy. In this work, a malware classification system proposed with the supervised machine learning of unknown malware instances through Support Vector Machine - Stochastic Gradient Descent (SVM-SGD) algorithm. The performance of the system evaluated on CIC-IDS2017 dataset with labelled attacks. The system is compared with traditional signature based detection model and observed to report less number of false alerts with improved accuracy. The signature based detection gets an accuracy of 86.12%, while the SVM-SGD gets the best accuracy of 99.13%. The model is found to be lightweight but efficient in detecting malware with high degree of accuracy.
Log-Based Authentication for Cloud Environments
Smart Computing Techniques and Applications, 2021
Computers & Electrical Engineering, 2018
Cloud computing is an archetype that enables access to a shared pool of computing resources for c... more Cloud computing is an archetype that enables access to a shared pool of computing resources for cloud users in an on-demand or pay-per-use, fashion. Cloud computing offers several benefits to users and organizations, in terms of capital expenditure and savings in operational expenditure. Despite the existence of such benefits, there are some obstacles that place restrictions on the usage of cloud computing. Security is a major issue that is always considered. The lack of this vital feature results in the negative impact of the computing archetype thus resulting in personal, ethical, and financial harm. This paper will focus and explore the security challenges that are faced by cloud entities. These entities include Cloud Service Provider, the Data Owner and Cloud User. Focusing on the crypto-cloud that constitutes of different Communication, Computation, and Service Level Agreement. Studying the causes and effects of various cyber attacks it will provide the necessary upgrades. 1. Introduction Cloud computing creates a network-based environment vision to the users, which paves way for the sharing of calculations and resources regardless of location. The National Institute of Standards and Technology's (NIST) defines cloud computing [1] as, "A template for providing the suitable and when needed access to the internet, to a collective pool of programmable grids, storage, servers, software, and amenities that can be rapidly emancipated, with little communication and supervision from the provider". The characteristics of the type of processing are exhibited in Fig. 1 as On-demand self-service, High-performance network access, Rapid Elasticity, Resource Pooling and Measured Service. It also depicts four deployment models namely Hybrid, Community, Private and Public clouds. This is then coupled with the three service models, which are, PAAS (Platform as a Service), IAAS (Infrastructure as a Service), and SAAS (Software as a Service). NIST's cloud computing definition provides the needed framework and common characteristics depicted such as Virtualization, Homogeneity, Geographic Distribution and Service Orientation among others. With all the layers of the cloud service models depicted in Fig. 2, security issues need to be addressed. When the layers are to be compared the high dependence of the browser position's it at the top whereas, the bottom layers are more web services oriented. Overall, a decrease in investment and operational expenses is achieved this is also followed by an increase in efficiency and scalability through the layers The service model deployed can be private, public, hybrid or community cloud as per the user requirements. Organization: The next two sections that follow indicate the security challenges. Sections 4-7 address the security challenges in communication, computational, data level and Service Level Agreement (SLA) level. Finally, Section 8, provides the conclusion with a comparison of the author's survey with other pre-existing reviews
Uploads
Papers by Nalini Subramanian