Nithya Chidambaram
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Nithya Chidambaram has a total of 45 co-authors. Here are the top co-authors by number of shared publications:
- Rengarajan Amirtharajan
School of Electrical & Electronics Engineering, SASTRA Deemed University, Thanjavur, India
10 shared publications Pethuru Raj
Reliance Jio Cloud Services (JCS), Bangalore, Karnataka, India
4 shared publicationsK Thenmozhi
Department of Electronics and Communication, SASTRA Deemed to be University, Thanjavur, Tamil Nadu, India
2 shared publicationsK. Thenmozhi
School of Computing, SASTRA Deemed University, Thanjavur, India
2 shared publications- Karuppuswamy Thenmozhi
School of Electrical & Electronics Engineering, SASTRA University, Thanjavur, India
2 shared publications Kunda Vineela
Department of Electronics and Communication, SASTRA Deemed to be University, Thanjavur, Tamil Nadu, India
2 shared publications
Latest Publications
- Open Access
- 1 April 2026
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 3191 (1)
A Machine Learning Influenced Cryptographic Framework for Fast and Efficient Encryption
In the realm of image encryption, a fundamental trade-off exists between computational complexity and the integrity of data transmission security. Traditional encryption methods, although robust, incur significant computational overhead, rendering them unsuitable for real-time or resource-constrained applications. The proposed research seeks to address this challenge by harnessing the power of machine learning (ML) model to optimize both efficiency and security. ML model is used to selectively identify and encrypt sensitive image regions, enhancing both security and efficiency. Texture, statistical features like entropy, energy, contrast, correlation and homogeneity are extracted using MATLAB to characterize an image block and subsequently classified using supervised learning algorithms. Support Vector Machine (SVM) achieved a classification accuracy of 99.35%. Identified regions are selectively encrypted using a 2D Henon map, coupled logistic sine map (CLS) for key generation. The framework integrates ML model and Image encryption. Experimental results confirm the robustness of the scheme against statistical, differential, noise, occlusion, and plaintext attacks, making it well-suited for secure image transmission.
- 1 April 2026
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 3191 (1)
Open AccessA Machine Learning Influenced Cryptographic Framework for Fast and Efficient Encryption
In the realm of image encryption, a fundamental trade-off exists between computational complexity and the integrity of data transmission security. Traditional encryption methods, although robust, incur significant computational overhead, rendering them unsuitable for real-time or resource-constrained applications. The proposed research seeks to address this challenge by harnessing the power of machine learning (ML) model to optimize both efficiency and security. ML model is used to selectively identify and encrypt sensitive image regions, enhancing both security and efficiency. Texture, statistical features like entropy, energy, contrast, correlation and homogeneity are extracted using MATLAB to characterize an image block and subsequently classified using supervised learning algorithms. Support Vector Machine (SVM) achieved a classification accuracy of 99.35%. Identified regions are selectively encrypted using a 2D Henon map, coupled logistic sine map (CLS) for key generation. The framework integrates ML model and Image encryption. Experimental results confirm the robustness of the scheme against statistical, differential, noise, occlusion, and plaintext attacks, making it well-suited for secure image transmission.
- Open Access
- 13 December 2025
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
A custom hash algorithm for hosting secure gray scale image repository in public cloud
Nowadays, Cloud computing is an essential platform for securing resources and effectively managing files. In digital technology, many data leaks or breaches frequently occur during the storage and transmission process. Several techniques for secure image transmission have been developed by researchers worldwide. In the traditional method, data loss prevention (DLP) is the best way to protect sensitive data from breaches. The massive amount of data is not feasible in the existing storage system. However, ensuring data security remains a severe challenge. Cloud infrastructure provides a more robust, reliable, and scalable solution to overcome attacks in developing regions. The primary objective of cloud storage is to provide affordable and easy access to storage, with a vast amount of data stored across multiple cloud storage services. This paper proposed a custom block-based hash algorithm that generates a digital fingerprint from the grayscale-scale image. The pivotal contribution presented in the proposed work lies in emphasising data integrity generation and validation, tamper detection, and accurate identification of the tampered region. The entire 256 × 256 image is considered for tamper-proofing, and the hash values generated are based on the proposed work. In the integrity validation process, it compares the digest with the original digest. The cloud environment provides scalable infrastructure for securely managing and storing the digital fingerprint. User-level authentication is also incorporated into the proposed framework. Additionally, a Graphical User Interface (GUI) application has been developed for generating a hash and verifying whether the image has been tampered with or not, with the tampered region marked by a bounding box. Various benchmark metrics are analysed for validating the outfit of the proposed algorithm. The metrics, including quantitative and qualitative tests for integrity codes, collision property, and avalanche effect, were analysed, and the proposed algorithm exhibits a good ability towards integrity validation.
- 13 December 2025
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessA custom hash algorithm for hosting secure gray scale image repository in public cloud
Nowadays, Cloud computing is an essential platform for securing resources and effectively managing files. In digital technology, many data leaks or breaches frequently occur during the storage and transmission process. Several techniques for secure image transmission have been developed by researchers worldwide. In the traditional method, data loss prevention (DLP) is the best way to protect sensitive data from breaches. The massive amount of data is not feasible in the existing storage system. However, ensuring data security remains a severe challenge. Cloud infrastructure provides a more robust, reliable, and scalable solution to overcome attacks in developing regions. The primary objective of cloud storage is to provide affordable and easy access to storage, with a vast amount of data stored across multiple cloud storage services. This paper proposed a custom block-based hash algorithm that generates a digital fingerprint from the grayscale-scale image. The pivotal contribution presented in the proposed work lies in emphasising data integrity generation and validation, tamper detection, and accurate identification of the tampered region. The entire 256 × 256 image is considered for tamper-proofing, and the hash values generated are based on the proposed work. In the integrity validation process, it compares the digest with the original digest. The cloud environment provides scalable infrastructure for securely managing and storing the digital fingerprint. User-level authentication is also incorporated into the proposed framework. Additionally, a Graphical User Interface (GUI) application has been developed for generating a hash and verifying whether the image has been tampered with or not, with the tampered region marked by a bounding box. Various benchmark metrics are analysed for validating the outfit of the proposed algorithm. The metrics, including quantitative and qualitative tests for integrity codes, collision property, and avalanche effect, were analysed, and the proposed algorithm exhibits a good ability towards integrity validation.
- Open Access
- 15 February 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-18
Reconfigurable security solution based on hopfield neural network for e-healthcare applications
In the healthcare sector, e-diagnosis through medical images is essential in a multi-speciality hospital; securing the medical images becomes crucial for preserving an individual’s privacy in e-healthcare applications. So, this paper has proposed a novel encryption scheme implemented on reconfigurable hardware. Realising image encryption schemes on FPGA hardware platforms offers substantial advantages over software implementations. The image-specific key and Hopfield Neural Network (HNN) carry out the diffusion process using the suggested encryption method. The confusion is accomplished simultaneously by the pseudo-random memory addresses derived via a 16-bit stream cipher circuit, which incorporates cryptography and neural network dynamics methods. By breaking up the spatial redundancy in image data, this diffusion mechanism increases the data’s resilience against statistical attacks, yielding an average entropy of 7.99 and near zero correlation. When implemented on an FPGA platform, this dual-layer encryption technique’s fast processing speed, parallelism, and reconfigurability are substantial benefits, especially for real-time and resource-constrained applications. FPGA implementation occupies 20% of the total hardware and 424.71 mW of power dissipation on Intel Cyclone V FPGA.
- 15 February 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-18
Open AccessReconfigurable security solution based on hopfield neural network for e-healthcare applications
In the healthcare sector, e-diagnosis through medical images is essential in a multi-speciality hospital; securing the medical images becomes crucial for preserving an individual’s privacy in e-healthcare applications. So, this paper has proposed a novel encryption scheme implemented on reconfigurable hardware. Realising image encryption schemes on FPGA hardware platforms offers substantial advantages over software implementations. The image-specific key and Hopfield Neural Network (HNN) carry out the diffusion process using the suggested encryption method. The confusion is accomplished simultaneously by the pseudo-random memory addresses derived via a 16-bit stream cipher circuit, which incorporates cryptography and neural network dynamics methods. By breaking up the spatial redundancy in image data, this diffusion mechanism increases the data’s resilience against statistical attacks, yielding an average entropy of 7.99 and near zero correlation. When implemented on an FPGA platform, this dual-layer encryption technique’s fast processing speed, parallelism, and reconfigurability are substantial benefits, especially for real-time and resource-constrained applications. FPGA implementation occupies 20% of the total hardware and 424.71 mW of power dissipation on Intel Cyclone V FPGA.
- Open Access
- 7 April 2023
- Published by MDPI AG in Mathematics
- Vol. 11 (8) , 1769
Neural Attractor-Based Adaptive Key Generator with DNA-Coded Security and Privacy Framework for Multimedia Data in Cloud Environments
Cloud services offer doctors and data scientists access to medical data from multiple locations using different devices (laptops, desktops, tablets, smartphones, etc.). Therefore, cyber threats to medical data at rest, in transit and when used by applications need to be pinpointed and prevented preemptively through a host of proven cryptographical solutions. The presented work integrates adaptive key generation, neural-based confusion and non-XOR, namely DNA diffusion, which offers a more extensive and unique key, adaptive confusion and unpredictable diffusion algorithm. Only authenticated users can store this encrypted image in cloud storage. The proposed security framework uses logistics, tent maps and adaptive key generation modules. The adaptive key is generated using a multilayer and nonlinear neural network from every input plain image. The Hopfield neural network (HNN) is a recurrent temporal network that updates learning with every plain image. We have taken Amazon Web Services (AWS) and Simple Storage Service (S3) to store encrypted images. Using benchmark evolution metrics, the ability of image encryption is validated against brute force and statistical attacks, and encryption quality analysis is also made. Thus, it is proved that the proposed scheme is well suited for hosting cloud storage for secure images.
- 7 April 2023
- Published by MDPI AG in Mathematics
- Vol. 11 (8) , 1769
Open AccessNeural Attractor-Based Adaptive Key Generator with DNA-Coded Security and Privacy Framework for Multimedia Data in Cloud Environments
Cloud services offer doctors and data scientists access to medical data from multiple locations using different devices (laptops, desktops, tablets, smartphones, etc.). Therefore, cyber threats to medical data at rest, in transit and when used by applications need to be pinpointed and prevented preemptively through a host of proven cryptographical solutions. The presented work integrates adaptive key generation, neural-based confusion and non-XOR, namely DNA diffusion, which offers a more extensive and unique key, adaptive confusion and unpredictable diffusion algorithm. Only authenticated users can store this encrypted image in cloud storage. The proposed security framework uses logistics, tent maps and adaptive key generation modules. The adaptive key is generated using a multilayer and nonlinear neural network from every input plain image. The Hopfield neural network (HNN) is a recurrent temporal network that updates learning with every plain image. We have taken Amazon Web Services (AWS) and Simple Storage Service (S3) to store encrypted images. Using benchmark evolution metrics, the ability of image encryption is validated against brute force and statistical attacks, and encryption quality analysis is also made. Thus, it is proved that the proposed scheme is well suited for hosting cloud storage for secure images.
- 27 February 2021
- Published by Springer Nature
- p. 671-682
A Dual 32 Nibble Specific Cipher Model for RGB Images Using Lorenz Attractor
- 27 February 2021
- Published by Springer Nature
- p. 671-682
A Dual 32 Nibble Specific Cipher Model for RGB Images Using Lorenz Attractor
- 13 November 2020
- Published by Springer Nature in Neural Computing and Applications
- Vol. 33 (12) , 6671-6684
Neural-assisted image-dependent encryption scheme for medical image cloud storage
- 13 November 2020
- Published by Springer Nature in Neural Computing and Applications
- Vol. 33 (12) , 6671-6684
Neural-assisted image-dependent encryption scheme for medical image cloud storage
- 25 September 2020
- Published by Springer Nature
- p. 487-496
A Crypto Model for Confuse-Cum-Diffuse RGB Images: A Near Zero Correlation Approach
- 25 September 2020
- Published by Springer Nature
- p. 487-496
A Crypto Model for Confuse-Cum-Diffuse RGB Images: A Near Zero Correlation Approach
- 19 October 2019
- Published by Springer Nature
- p. 404-416
Tri Layer Model for Color Image Ciphering Through DNA Assisted 2D Chaos
- 19 October 2019
- Published by Springer Nature
- p. 404-416
Tri Layer Model for Color Image Ciphering Through DNA Assisted 2D Chaos
- 19 October 2019
- Published by Springer Nature
- p. 491-498
Tamper Detection of Medical Images Using Modified Hashing Algorithm
- 19 October 2019
- Published by Springer Nature
- p. 491-498
Tamper Detection of Medical Images Using Modified Hashing Algorithm
- 1 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 759-763
DNA Coupled Chaos for Unified Color Image Encryption - a Secure Sharing Approach
In the era of computing, internet and networking plays one of the vital roles. For communication, today a large transmission of multimedia messages in the form of images take place. Many techniques have been proposed to establish a secure communication, in which data hiding and image encryption are two main techniques. In this paper an encryption algorithm is proposed. In this algorithm, a plain color image is split into its three RGB planes, confuse them and combine to form the final encrypted image. Even by implementing this simple algorithm, satisfactory results are obtained.
- 1 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 759-763
DNA Coupled Chaos for Unified Color Image Encryption - a Secure Sharing Approach
In the era of computing, internet and networking plays one of the vital roles. For communication, today a large transmission of multimedia messages in the form of images take place. Many techniques have been proposed to establish a secure communication, in which data hiding and image encryption are two main techniques. In this paper an encryption algorithm is proposed. In this algorithm, a plain color image is split into its three RGB planes, confuse them and combine to form the final encrypted image. Even by implementing this simple algorithm, satisfactory results are obtained.