Proactive Zero-Trust Intrusion Detection for Consumer IoT Applications Using Lightweight Ensemble Learning With Anomaly Analysis Bipasha Guha Roy, Deepsubhra Guha Roy, Piyali Datta, Surbhi Bhatia Khan, Asma Alshuhail, Oumaima Saidani IEEE Transactions on Consumer Electronics, 2026 The rapid proliferation of consumer IoT devices from smart home hubs to wearables has expanded the attack surface, introducing new security and privacy challenges. Traditional Intrusion Detection Systems (IDS) often rely on implicit trust and heavyweight computation, making them unsuitable for resource-constrained consumer electronics. This paper presents a proactive, lightweight zero-trust IDS tailored for consumer applications. Our two-layer architecture integrates a supervised stacked ensemble classifier (Random Forest, XGBoost, Light-GBM) to detect known threats and an unsupervised DBSCAN (Density-Based Spatial Clustering of Applications with Noise)-based anomaly detector to identify zero-day attacks. We introduce a feature reduction pipeline driven by correlation and variance analysis, reducing the feature set by over 50% to fit edge hardware constraints. Evaluated on the CICIDS collection dataset (over 9 million flows), the framework achieves 98.48% accuracy while maintaining real-time processing capability on Raspberry Pi-class hardware. By continuously scrutinizing both malicious and benign traffic, our system delivers proactive, trust-enhancing defense critical to modern consumer IoT applications.
Exploring Reinforcement Learning in Autonomous Robot Path Planning and Obstacle Navigation Uday Sankar Mukherjee, Mousumi Laha, Piyali Datta 2025 8th International Conference on Electronics Materials Engineering and Nano Technology Iementech 2025, 2025 The article deals with issues concerning the au-tonomous planning of trajectories and avoiding obstacles for mobile robots using reinforcement learning. The emphasis is on dynamic tasks performed by robots devoid of any prior knowledge or maps of the operating environment. In those conditions, conventional motion planning techniques do not work; however, Deep Reinforce-ment Learning (DRL) is a solution. DRL allows robots to learn and adapt independently while operating in real-time without human intervention, even in the most complicated environments. The research investigates different approaches including Q-learning, SARSA, and DQN algorithms, aiming to evaluate their differences based on the path length and the computational time in reaching that path. The findings confirm that DQN salvages SARSA and Q-learning in terms of efficiency and path optimization. The main focus of the research paper is the fusion of deep learning and reinforcement learning that enables the processing of the sensor to decision making, which in turn enhances the ability of the robot to navigate. The results of the experiments support the applicability of these methods in dynamic scenarios.
A Machine Learning-based Attack-Preventive Synthesis for Cyber-Physical DMFBs Piyali Datta, Arpan Chakraborty, Rajat Kumar Pal IETE Journal of Research, 2025 A digital microfluidic biochip (DMFB) with cyber-physical adaptation is undeniably susceptible to attack due to high network connection. A number of leading researches are carried out to assess various attacks and their impacts. Several defence mechanisms are developed by arranging on-chip monitoring systems through deployment of checkpoints. However, the synthesis phase in DMFB plays a crucial role to realize a given bio-protocol by modelling it as a bioassay graph, placing mixing modules on the chip, and carrying out on-chip droplet routes. An attack-preventive synthesis that can execute a bioassay in a vulnerable environment is immensely important. Here, an attack-preventive synthesis is proposed that deals with denial-of-service attacks. A predictive model is developed following a machine learning-based approach to enable the synthesis phase for anticipating the impact of various attack scenarios. A probabilistic analysis is presented to measure safeness of a bioassay under an attack-prone scenario. The model is evaluated over a wide-ranged dataset.
Codesign for Broadcast Addressing Biochip Towards Tamper-Resistance and Enhanced Reliability Ritwika Majumdar, Piyali Datta, Arpan Chakraborty, Rajat Kumar Pal Proceedings of the IEEE International Conference on VLSI Design, 2025 Digital Microfluidic Biochips (DMFB), famous for their low manufacturing cost and high responsiveness, have shown vulnerability to actuation sequence tampering attacks with the motive of manipulating assay results. Broadcast addressing is a specialized pin-mapping scheme whose highly programmable nature can be leveraged to expose the effect of stealthy actuation tampering attacks via networks. State-of-the-art research producing tamper-resistant outcome do not ensure feasible wire-routing. Moreover, higher electrode switching activity degrades reliability of a biochip. There must be a codesign considering all these design, security, and reliability issues together for attaining safe and potential deliverables. As per our knowledge, this paper introduces the first pin-mapping method for broadcast addressing biochips addressing the problems of tamper-resistance, wire-routing, and switching toggles. Experimental results show that our method improves the design significantly in terms of well-known tamper-resistance metrics, provides a pin-mapping solution with feasible wire-routing, and potentially reduces switching toggles which in turn enhance reliability of the chip.
Towards Minimal-Telemetry VM Rightsizing: A Lifecycle-Anchored Morphology Approach Sarnaavho Pal, Shirsendu Roy, Deepsubhra Guha Roy, Piyali Datta 13th International Conference on Intelligent Embedded Microelectronics Communication and Optical Networks Iemecon 2025, 2025 Cloud providers face high inefficiencies due to overprovisioned virtual machines (VMs) and churn of short-lived deployments. Existing rightsizing and autoscaling approaches rely on rich telemetry, but often overlook VM lifecycle patterns. We propose a minimal-telemetry, lifecycle-anchored taxonomy of VM morphologies, defined by simple statistics (average, p95, maximum CPU) and lifetime. Using Gaussian Mixture Models, we cluster workloads into operationally meaningful classes, and demonstrate predictive power for identifying short-lived VMs (recall <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\approx 92 \%)$</tex> using Random Forest and XGBoost. This taxonomy enables actionable policies such as early termination of toxic workloads, isolation of unstable clusters, and promotion of reliable ones. We present results on a large VM dataset and show cost, reliability, and sustainability benefits.
Quality of Experience Aware Service Selection Model to Empower Edge Computing in IoT Bipasha Guha Roy, Deepsubhra Guha Roy, Piyali Datta, Surbhi Bhatia Khan, Abdullah Albuali, Ahlam Almusharraf International Journal of Distributed Sensor Networks, 2025 Quality of experience‐aware service selection can significantly remove well‐known scalability issues of an Internet of Things (IoT) architecture. In traditional IoT architecture, several heterogeneous data streams from connected nodes are transmitted through gateways to the remote mobile cloud servers. The entire procedure is time‐ and energy‐consuming if the target dataset is comparatively small and uninterrupted. Also, using this conventional technique, the reliability grade drops significantly to meet additional security‐related quality of service (QoS) requirements compared to the service cost. We propose a quality of experience‐aware task rescheduling model using edge modules that offer territory‐based three‐layered edge IoT data analysis and service selection. The observation module at the application layer takes a near‐optimal remark upon each usage metric having distinct QoS components. Meanwhile, the QoS manager at the network layer handles network traffic due to the load associated with heterogeneous service needs. The precision of the knowledge is assured to the service manager through the sensing layer with few adaptability characteristics towards assorted service requests. The proposed three‐layered energy‐efficient model helps minimize data delivery time with minimal cost and optimized quality assurance for service‐based IoT infrastructures like smart agriculture, patient monitoring, and student monitoring.
Quality of Service-Aware 6G- Enabled NB-IoT for Health Monitoring in Long Distance High-Speed Trains Bipasha Guha Roy, Deepsubhra Guha Roy, Piyali Dutta, Surbhi Bhatia Khan, Fatima Asiri, Manel Ayadi IEEE Transactions on Consumer Electronics, 2025 Internet of Things connectivity in home health monitoring is a high-in-demand application area. The electronics industry and procedural researchers seek high-end, secured, on-time, cost-effective ways to build reliable quality of service (QoS) proved autonomous systems using existing wireless techniques. Also, the continuous availability of a traffic-free gateway, particularly in isolated places, is necessary for large-scale data gathering and real-time data update processes to function the sensor nodes in an Internet of Things (IoT) network. Improved Narrowband IoT (NB-IoT) is one of the most desirable networks offered by 6th generation (6G) connectivity in IoT-associated remote-monitoring proceedings. In this article, we propose a QoS-aware narrow bandwidth allocation-based prototype model for healthcare monitoring in long-distance high-speed trains during the patient transfer from home to the healthcare center or vice versa. This article demonstrates a possible enhancement in social aspects of cognitive IoT applications with large data systems in industrial informatics.
An endeavour to find two unequal false coins Joydeb Ghosh, Piyali Datta, Arpan Chakraborty, Ankita Nandy, Lagnashree Dey, Rajat Kumar Pal, Ranjit Kumar Samanta 8th International Conference on Electrical and Computer Engineering Advancing Technology for A Better Tomorrow Icece 2014, 2015
The first algorithm for solving two coins counterfeiting with ω(ΔH) = ω(ΔL) Joydeb Ghosh, Arpan Chakraborty, Piyali Datta, Lagnashree Dey, Ankita Nandy, Rajat Kumar Pal, Ranjit Kumar Samanta 8th International Conference on Electrical and Computer Engineering Advancing Technology for A Better Tomorrow Icece 2014, 2015
