Kranthi Kumar SIngamaneni
@gitam.edu
Assistant Professor , Computer Science and Engineering
Gandhi Institute of Technology and Management, formerly GITAM University
RESEARCH INTERESTS
cloud security, cyber security, applied cryptography, data science
Scopus Publications
Scopus Publications
Sathuluri Raju, Kranthi Kumar Singamaneni, Lim Boon Hooi, Kunche Usha Rani, and Chandrika B.
Springer Science and Business Media LLC
Kranthi Kumar Singamaneni, Meghamala Bag, Tanmaya Bhoi, Abhijit Joshi, Soumya Ranjan Bhoi, and Debabrata Dansana
Springer Science and Business Media LLC
Ramesh Babu Pittala, Medikonda Asha Kiran, Niteesha Sharma, Manyam Thaile, Kranthi Kumar Singamaneni, Lakshmi Prasanna Byrapuneni, Yerraganti Krishna Bhargavi, and Peddada Nagamani
SAGE Publications
In text classification tasks with complex models and high-stakes domains the alignment between predictions and explanations tends to be weak because post-hoc explainability methods operate independent of model training. In this paper, we suggest ATM-AM - an approach based on the Gated Recurrent Unit (GRU) that combines Bahdanau attention with a training-time SHAP-backed alignment objective to offer real-time, context-aware interpretability without trade-off in predictive performance. The model is tested over three frequently-used sentiment analysis datasets (IMDbhttps://huggingface.co/datasets/imdb, Amazon Reviews https://www.kaggle.com/datasets/bittlingmayer/amazonreviews, and SST-2. https://huggingface.co/datasets/glue/viewer/sst2) yielding accuracy scores of 91.8%, 89.5%, and 90.0% with respective F1-scores of 0.899, 0.877, and 0.889 respectively, on each dataset. We also average our measurements over three runs for statistical soundness. The additional training latency added by ATM-AM is quite modest (13–18%), and the inference time remains short (3–4 ms per sample), rendering it feasible to be deployed in real-time. A user-centered interpretability study with 30 participants obtained an average rating of 4.6/5 showing that users trust the explanations produced by our proposed model. These observations posit ATM-AM as a feasible and interpretable solution Text Classification in contexts where model behavior needs to be accountable and reliable.
Kranthi Kumar Singamaneni, Kusum Yadav, Arwa N. Aledaily, Wattana Viriyasitavat, Gaurav Dhiman, and Amandeep Kaur
Springer Science and Business Media LLC
Kranthi Kumar Singamaneni, Anil Kumar Budati, Shayla Islam, Raenu Kolandaisamy, and Ghulam Muhammad
Institute of Electrical and Electronics Engineers (IEEE)
Rakesh Salakapuri, Kranthi Kumar Singamaneni, Panduranga Vital Terlapu, Balakrishna Peesala, Siva Naga Raju B, and Ravikiran Reddy Kandadi
IEEE
Kranthi Kumar Singamaneni and Ghulam Muhammad
Elsevier BV
Kranthi Kumar Singamaneni, Ghulam Muhammad, and Zulfiqar Ali
Institute of Electrical and Electronics Engineers (IEEE)
Kranthi Kumar Singamaneni, Ghulam Muhammad, and Zulfiqar Ali
Institute of Electrical and Electronics Engineers (IEEE)
The domain of Mobile Edge Computing (MEC) has seen rapid growth, making consumer behavior research an essential element in many applications. Nevertheless, in MEC systems that are decentralized and have limited resources, challenges arise in ensuring both data integrity and access control. This paper introduces a new technique called Quantum Hash-Based Attribute-Based Encryption (QH-ABE) to address these issues. Previously, there were several methods available to guarantee data integrity and access control in MEC. However, these systems had limits in managing large and intricate datasets, lacked a standardized protocol for revocation, and incurred significant computational costs. We were prompted by these restrictions to suggest a more efficient technique, which included using the QH-ABE method in our study. The suggested solution integrates hash functions with quantum computing concepts to enhance security and control access in MEC-enabled consumer behavior research. The suggested technique provides several benefits compared to traditional hash algorithms by using hash functions. In this technique, we introduce a Recursive Non-Linear Polynomial graph-centered Integrity Algorithm (RNLPIA). RNLPIA enhances security by thwarting covert alterations to data and guaranteeing tamper-evident measures via the generation of unique hash values derived from the content of the data. The suggested method’s efficacy and efficiency are proved by a comprehensive experimental assessment, highlighting its capability to fulfill the data integrity and access control needs of MEC situations. The performance of our technology showcases its potential and paves the way for using quantum computing technologies for accessing control and data security. This work contributes to the progress of privacy-preserving, secure consumer behavior analysis in the dynamic MEC environment.
Kranthi Kumar Singamaneni, Anil Kumar Budati, and Thulasi Bikku
Springer Science and Business Media LLC
Venkateswarlu Gundu, Kranthi Kumar Singamaneni, Ramesh G., Prabhakar Kandukuri, Deepti Sharma, and Madhavi Karanam
EDP Sciences
Internet of Things (IoT) innovation is one of the fastest growing fields in various regions or aspects which include irrigation. IoT works on the character of our lives by way of bringing and cultivating modifications in many fields of exercises to motive them to come to be convenient, savvy and enriched with the aid of adequate guy-made recognition. As a result of this innovation, smart cultivating frameworks recognize a social trade towards current agri-business that is more useful, consumes less water, and is extraordinarily less luxurious. The primary goal of this paper is to make use of IoT within the agribusiness subject to accumulate facts right away (soil Moister, temperature), with a purpose to help one with staring at a few climate situations distantly, effectively and improve massively the creation and thus the pay of ranchers. The modern version is created utilizing NodeMCU innovation, which contains express sensors, and a Wifi module that assists with amassing moment records on the internet. It is worth concentrating on the testing of this model created, profoundly precise data in light of the fact that any herbal changes were outstanding in a flash and taking into consideration to decide. This paper speculating about integrating the IoT with different other technologies.
Prabhakar Kandukuri, B. Sameer Sowrab, G. Ramesh, and Kranthi Kumar Singamaneni
IEEE
The main food that people in India consume on a daily basis is paddy. According to data, the stress caused by rice illnesses, which reduce yields by 70%, was felt by the paddy farmers. If not controlled within a certain time frame, these plant diseases, which are typically brought on by pests, insects, and pathogens, have a significant negative impact on productivity. This research proposed auto encoders rooting convolutional neural network model to control these paddy diseases, and it has been implemented with various per-trained models like Vgg16, Resnet50, and inceptionV6. This model accurately determines whether a paddy plant is healthy or has one of four different types of paddy diseases. These models were developed, tested using auto encoders and a dataset of thermal pictures that was made available to the public, and they achieved the maximum model accuracy of 90.6%. A 84.8% was attained in the prior iteration without the use of auto encoders. With the use of this model, people can quickly detect paddy illness and assist farmers in raising productivity and yield.
Kranthi Kumar Singamaneni, Ali Nauman, Sapna Juneja, Gaurav Dhiman, Wattana Viriyasitavat, Yasir Hamid, and Joseph Henry Anajemba
MDPI AG
Cloud computational service is one of the renowned services utilized by employees, employers, and organizations collaboratively. It is accountable for data management and processing through virtual machines and is independent of end users’ system configurations. The usage of cloud systems is very simple and easy to organize. They can easily be integrated into various storages of the cloud and incorporated into almost all available software tools such as Hadoop, Informatica, DataStage, and OBIEE for the purpose of Extraction-Transform-Load (ETL), data processing, data reporting, and other related computations. Because of this low-cost-based cloud computational service model, cloud users can utilize the software and services, the implementation environment, storage, and other on-demand resources with a pay-per-use model. Cloud contributors across this world move all these cloud-based apps, software, and large volumes of data in the form of files and databases into enormous data centers. However, the main challenge is that cloud users cannot have direct control over the data stored at these data centers. They do not even know the integrity, confidentiality, level of security, and privacy of their sensitive data. This exceptional cloud property creates several different security disputes and challenges. To address these security challenges, we propose a novel Quantum Hash-centric Cipher Policy-Attribute-based Encipherment (QH-CPABE) framework to improve the security and privacy of the cloud user’s sensitive data. In our proposed model, we used both structured and unstructured big cloud clinical data as input so that the simulated experimental results conclude that the proposal has precise, resulting in approximately 92% correctness of bit hash change and approximately 96% correctness of chaotic dynamic key production, enciphered and deciphered time as compared with conventional standards from the literature.
Kranthi Kumar Singamaneni, Gaurav Dhiman, Sapna Juneja, Ghulam Muhammad, Salman A. AlQahtani, and John Zaki
MDPI AG
The industry-based internet of things (IIoT) describes how IIoT devices enhance and extend their capabilities for production amenities, security, and efficacy. IIoT establishes an enterprise-to-enterprise setup that means industries have several factories and manufacturing units that are dependent on other sectors for their services and products. In this context, individual industries need to share their information with other external sectors in a shared environment which may not be secure. The capability to examine and inspect such large-scale information and perform analytical protection over the large volumes of personal and organizational information demands authentication and confidentiality so that the total data are not endangered after illegal access by hackers and other unauthorized persons. In parallel, these large volumes of confidential industrial data need to be processed within reasonable time for effective deliverables. Currently, there are many mathematical-based symmetric and asymmetric key cryptographic approaches and identity- and attribute-based public key cryptographic approaches that exist to address the abovementioned concerns and limitations such as computational overheads and taking more time for crucial generation as part of the encipherment and decipherment process for large-scale data privacy and security. In addition, the required key for the encipherment and decipherment process may be generated by a third party which may be compromised and lead to man-in-the-middle attacks, brute force attacks, etc. In parallel, there are some other quantum key distribution approaches available to produce keys for the encipherment and decipherment process without the need for a third party. However, there are still some attacks such as photon number splitting attacks and faked state attacks that may be possible with these existing QKD approaches. The primary motivation of our work is to address and avoid such abovementioned existing problems with better and optimal computational overhead for key generation, encipherment, and the decipherment process compared to the existing conventional models. To overcome the existing problems, we proposed a novel dynamic quantum key distribution (QKD) algorithm for critical public infrastructure, which will secure all cyber–physical systems as part of IIoT. In this paper, we used novel multi-state qubit representation to support enhanced dynamic, chaotic quantum key generation with high efficiency and low computational overhead. Our proposed QKD algorithm can create a chaotic set of qubits that act as a part of session-wise dynamic keys used to encipher the IIoT-based large scales of information for secure communication and distribution of sensitive information.
Kranthi Kumar Singamaneni and P. Sanyasi Naidu
Inderscience Publishers
Kranthi Singamaneni, Abdullah Shawan Alotaibi, Sri Vijaya K, and Purnendu Shekhar Pandey
The Electrochemical Society
Mobile Ad hoc NETwork (MANET) is a type of network that is built by connecting a number of mobile devices together in a temporary manner through impermanent connections. Through broadcasting, the information should be distributed to all nodes in the network. A MANET is a network of self-configurable mobile nodes that are connected wirelessly. The security aspect of MANET is a major challenge, and there is a great deal of research being done in this area. The availability of energy is a critical criterion for a decentralised network. The protocol for AODV and DSR routing, as well as the security of the black hole node, are all investigated in this study. Protocols that are used during the route discovery process are particularly vulnerable to attack by the black hole. The goal of this survey, as a result, is to thoroughly investigate black hole attacks while also evaluating the performance of AODV and DSR during black hole attack scenarios. With Network Simulator 3, the work is completed by simulating both protocols under normal operation as well as under a black hole attack. The work is completed with Network Simulator 3 by simulating both protocols under a black hole attack (NS-3). AODV is more vulnerable to a black hole attack than the DSR, according to the results of simulations, and this vulnerability is greater under normal operating conditions. It has been discovered that MANET attacks are carried out with the assistance of a "black hole," according to simulation results.
M. Kiran Kumar, S. Kranthi Kumar, Ella Kalpana, Donapati Srikanth, and K. Saikumar
Springer International Publishing
Kranthi Kumar Singamaneni, Abhinav Juneja, Mohammed Abd-Elnaby, Kamal Gulati, Ketan Kotecha, and A. P. Senthil Kumar
Hindawi Limited
Topics such as computational sources and cloud-based transmission and security of big data have turned out to be a major new domain of exploration due to the exponential evolution of cloud-based data and grid facilities. Various categories of cloud services have been utilized more and more widely across a variety of fields like military, army systems, medical databases, and more, in order to manage data storage and resource calculations. Attribute-based encipherment (ABE) is one of the more efficient algorithms that leads to better consignment and safety of information located within such cloud-based storage amenities. Many outmoded ABE practices are useful for smaller datasets to produce fixed-size cryptograms with restricted computational properties, in which their characteristics are measured as evidence and stagnant standards used to generate the key, encipherment, and decipherment means alike. To surmount the existing problems with such limited methods, in this work, a dynamic nonlinear poly randomized quantum hash system is applied to enhance the safety of cloud-based information. In the proposed work, users’ attributes are guaranteed with the help of a dynamic nonlinear poly randomized equation to initialize the chaotic key, encipherment, and decipherment. In this standard, structured and unstructured big data from clinical datasets are utilized as inputs. Real-time simulated outcomes demonstrate that the stated standard has superior exactness, achieving over 90% accuracy with respect to bit change and over 95% accuracy with respect to dynamic key generation, encipherment time, and decipherment time compared to existing models from the field and literature. Experimental results are demonstrated that the proposed cloud security standard has a good efficiency in terms of key generation, encoding, and decoding process than the conventional methods in a cloud computing environment.
Thejovathi Murari, L. Prathiba, Kranthi Kumar Singamaneni, D. Venu, Vinay Kumar Nassa, Rachna Kohar, and Satyajit Sidheshwar Uparkar
Computers, Materials and Continua (Tech Science Press)
Singamaneni Kranthi Kumar, Alhassan Alolo Abdul-Rasheed Akeji, Tiruvedula Mithun, M. Ambika, L. Jabasheela, Ranjan Walia, and U. Sakthi
Computers, Materials and Continua (Tech Science Press)
Kranthi Kumar Singamaneni, Kadiyala Ramana, Gaurav Dhiman, Saurabh Singh, and Byungun Yoon
MDPI AG
As a result of the limited resources available in IoT local devices, the large scale cloud consumer’s data that are produced by IoT related machines are contracted out to the cloud. Cloud computing is unreliable, using it can compromise user privacy, and data may be leaked. Because cloud-data and grid infrastructure are both growing exponentially, there is an urgent need to explore computational sources and cloud large-data protection. Numerous cloud service categories are assimilated into numerous fields, such as defense systems and pharmaceutical databases, to compute information space and allocation of resources. Attribute Based Encryption (ABE) is a sophisticated approach which can permit employees to specify a higher level of security for data stored in cloud storage facilities. Numerous obsolete ABE techniques are practical when applied to small data sets to generate cryptograms with restricted computational properties; their properties are used to generate the key, encrypt it, and decrypt it. To address the current concerns, a dynamic non-linear polynomial chaotic quantum hash technique on top of secure block chain model can be used for enhancing cloud data security while maintaining user privacy. In the proposed method, customer attributes are guaranteed by using a dynamic non- polynomial chaotic map function for the key initialization, encryption, and decryption. In the proposed model, both organized and unorganized massive clinical data are considered to be inputs for reliable corroboration and encoding. Compared to existing models, the real-time simulation results demonstrate that the stated standard is more precise than 90% in terms of bit change and more precise than 95% in terms of dynamic key generation, encipherment, and decipherment time.