Kamalakanta Sethi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kamalakanta Sethi has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Munmun Swain2 shared publications
- Nikhil Tripathi
Department of Computer Science and Engineering, Indian Institute of Technology (Indian School of Mines), Dhanbad, India
2 shared publications - Bishwajeet Sahoo
Indian Institute of Information Technology, Sri City, Chittoor, Andhra Pradesh, India
1 shared publication Dinesh Mohanty
IIT Bhubaneswar, Kansapada, India
1 shared publication- Gyanendra Prasad Joshi
Department of Advanced AI Engineering, Kangwon National University, Samcheok, Republic of Korea
1 shared publication - Kasturi Dhal
Silicon University, Bhubaneswar, India
1 shared publication
Latest Publications
- 2 November 2026
- Published by Elsevier in Computers & Security
- Vol. 173
A newly generated dataset and pattern-driven approach for detecting AMQP Denial-of-Service attacks
- 2 November 2026
- Published by Elsevier in Computers & Security
- Vol. 173
A newly generated dataset and pattern-driven approach for detecting AMQP Denial-of-Service attacks
- Open Access
- 12 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 142948-142960
Lightweight DWT Steganography With ECC-ChaCha20 for Secure Medical IoT Systems
The rapid integration of the Internet of Things (IoT) into healthcare systems has raised concerns about the confidentiality and integrity of patient data transmitted over these networks. Although traditional cryptographic solutions, such as Rivest-Shamir-Adleman (RSA) and Advanced Encryption Standard (AES), are secure, they often introduce significant computational and energy overheads that are unsuitable for constrained Internet of Things (IoT) devices. This paper proposes a lightweight stego-crypto framework that combines ChaCha20 encryption and Elliptic Curve Cryptography (ECC) for efficient key management with a 2D Discrete Wavelet Transform (DWT)-based steganographic technique. The proposed model embeds encrypted diagnostic text within medical images, ensuring secure and imperceptible transmission of sensitive information. Extensive evaluations on grayscale medical images demonstrate superior performance across various metrics, including Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), Bit Error Rate (BER), Correlation, and system-level metrics such as CPU, memory, and power usage. Robustness against common image perturbations such as Gaussian noise, salt-and-pepper noise, JPEG compression, blurring, rotation, and translation is assessed using Bit Error Rate (BER) and payload correlation. Compared to RSA-AES and other conventional stego-crypto systems, our approach achieves a better trade-off between security, imperceptibility, and computational efficiency, making it highly suitable for real-time healthcare applications over IoT networks.
- 12 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 142948-142960
Open AccessLightweight DWT Steganography With ECC-ChaCha20 for Secure Medical IoT Systems
The rapid integration of the Internet of Things (IoT) into healthcare systems has raised concerns about the confidentiality and integrity of patient data transmitted over these networks. Although traditional cryptographic solutions, such as Rivest-Shamir-Adleman (RSA) and Advanced Encryption Standard (AES), are secure, they often introduce significant computational and energy overheads that are unsuitable for constrained Internet of Things (IoT) devices. This paper proposes a lightweight stego-crypto framework that combines ChaCha20 encryption and Elliptic Curve Cryptography (ECC) for efficient key management with a 2D Discrete Wavelet Transform (DWT)-based steganographic technique. The proposed model embeds encrypted diagnostic text within medical images, ensuring secure and imperceptible transmission of sensitive information. Extensive evaluations on grayscale medical images demonstrate superior performance across various metrics, including Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), Bit Error Rate (BER), Correlation, and system-level metrics such as CPU, memory, and power usage. Robustness against common image perturbations such as Gaussian noise, salt-and-pepper noise, JPEG compression, blurring, rotation, and translation is assessed using Bit Error Rate (BER) and payload correlation. Compared to RSA-AES and other conventional stego-crypto systems, our approach achieves a better trade-off between security, imperceptibility, and computational efficiency, making it highly suitable for real-time healthcare applications over IoT networks.
- 26 May 2025
- Published by Elsevier in Computers & Security
- Vol. 157
Identifying communication sequence anomalies to detect DoS attacks against MQTT
- 26 May 2025
- Published by Elsevier in Computers & Security
- Vol. 157
Identifying communication sequence anomalies to detect DoS attacks against MQTT
- Open Access
- 17 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 121444-121464
Analysis of Continual Learning Models for Intrusion Detection System
Deep Learning based Intrusion Detection Systems (IDSs) have received significant attention from the research community for their capability to handle modern-day security systems in large-scale networks. Despite their considerable improvement in performance over machine learning-based techniques and conventional statistical models, deep neural networks (DNN) suffer from catastrophic forgetting: the model forgets previously learned information when trained on newer data points. This vulnerability is specifically exaggerated in large scale systems due to the frequent changes in network architecture and behaviours, which leads to changes in data distribution and the introduction of zero-day attacks; this phenomenon is termed as covariate shift. Due to these constant changes in the data distribution, the DNN models will not be able to consistently perform at high accuracy and low false positive rate (FPR) rates without regular updates. However, before we update the DNN models, it is essential to understand the magnitude and nature of the drift in the data distribution. In this paper, to analyze the drift in data distribution, we propose an eight-stage statistics and machine learning guided implementation framework that objectively studies and quantifies the changes. Further, to handle the changes in data distribution, most IDS solutions collect the network packets and store them to retrain the DNN models periodically, but when the network’s size and complexity increase, those tasks become expensive. To efficiently solve this problem, we explore the potential of continual learning models to incrementally learn new data patterns while also retaining their previous knowledge. We perform an experimental and analytical study of advanced intrusion detection systems using three major continual learning approaches: learning without forgetting, experience replay, and dark experience replay on the NSL-KDD and the CICIDS 2017 dataset. Through extensive experimentation, we show that our continual learning models achieve improved accuracy and lower FPR rates when compared to the state-of-the-art works while also being able to incrementally learn newer data patterns. Finally, we highlight the drawbacks of traditional statistical and non-gradient based machine learning approaches in handling the covariate shift problem.
- 17 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 121444-121464
Open AccessAnalysis of Continual Learning Models for Intrusion Detection System
Deep Learning based Intrusion Detection Systems (IDSs) have received significant attention from the research community for their capability to handle modern-day security systems in large-scale networks. Despite their considerable improvement in performance over machine learning-based techniques and conventional statistical models, deep neural networks (DNN) suffer from catastrophic forgetting: the model forgets previously learned information when trained on newer data points. This vulnerability is specifically exaggerated in large scale systems due to the frequent changes in network architecture and behaviours, which leads to changes in data distribution and the introduction of zero-day attacks; this phenomenon is termed as covariate shift. Due to these constant changes in the data distribution, the DNN models will not be able to consistently perform at high accuracy and low false positive rate (FPR) rates without regular updates. However, before we update the DNN models, it is essential to understand the magnitude and nature of the drift in the data distribution. In this paper, to analyze the drift in data distribution, we propose an eight-stage statistics and machine learning guided implementation framework that objectively studies and quantifies the changes. Further, to handle the changes in data distribution, most IDS solutions collect the network packets and store them to retrain the DNN models periodically, but when the network’s size and complexity increase, those tasks become expensive. To efficiently solve this problem, we explore the potential of continual learning models to incrementally learn new data patterns while also retaining their previous knowledge. We perform an experimental and analytical study of advanced intrusion detection systems using three major continual learning approaches: learning without forgetting, experience replay, and dark experience replay on the NSL-KDD and the CICIDS 2017 dataset. Through extensive experimentation, we show that our continual learning models achieve improved accuracy and lower FPR rates when compared to the state-of-the-art works while also being able to incrementally learn newer data patterns. Finally, we highlight the drawbacks of traditional statistical and non-gradient based machine learning approaches in handling the covariate shift problem.