Adaptive Sensitivity-Aware Differential Privacy Accounting for Federated Smart-Meter Theft Detection Diego Labate, Dipanwita Thakur, Giancarlo Fortino Big Data and Cognitive Computing, 2026 Smart-meter theft detection requires learning from fine-grained electricity consumption data, whose centralized processing poses significant privacy risks. Federated learning (FL) mitigates these risks by decentralizing training, but providing rigorous user-level differential privacy (DP) under non-IID data and heterogeneous client behavior remains challenging. Existing DP-FL approaches rely on fixed global clipping bounds for client updates, which substantially overestimate sensitivity when privacy loss is composed using Rényi Differential Privacy (RDP), zero-Concentrated DP (zCDP), or Moments Accountant (MA) frameworks, leading to excessive noise and degraded utility. This work proposes an adaptive clipping-based RDP accountant that incorporates empirical, round-wise update magnitudes into privacy accounting by rescaling each round’s RDP contribution according to the observed clipping ratio. The method is optimizer-agnostic and is evaluated with FedAvg, FedProx, and SCAFFOLD on the SGCC smart-meter theft dataset under IID and Dirichlet non-IID partitions. Experimental results show consistently tighter privacy bounds and improved model utility compared to classical DP accountants, demonstrating the effectiveness of sensitivity-aware privacy accounting for practical differentially private FL.
Green Federated Learning: A New Era of Green Aware AI Dipanwita Thakur, Antonella Guzzo, Giancarlo Fortino, Francesco Piccialli ACM Computing Surveys, 2025 The development of AI applications, especially in large-scale wireless networks, is growing exponentially, alongside the size and complexity of the architectures used. Particularly, machine learning is acknowledged as one of today’s most energy-intensive computational applications, posing a significant challenge to the environmental sustainability of next-generation intelligent systems. Achieving environmental sustainability entails ensuring that every AI algorithm is designed with sustainability in mind, integrating green considerations from the architectural phase onwards. Recently, Federated Learning (FL), with its distributed nature, presents new opportunities to address this need. Hence, it is imperative to elucidate the potential and challenges stemming from recent FL advancements and their implications for sustainability. Moreover, it is crucial to furnish researchers, stakeholders, and interested parties with a roadmap to navigate and understand existing efforts and gaps in green-aware AI algorithms. This survey primarily aims to achieve this objective by identifying and analyzing over a hundred FL works and assessing their contributions to green-aware artificial intelligence for sustainable environments, with a specific focus on IoT research. It delves into current issues in green federated learning from an energy-efficient standpoint, discussing potential challenges and future prospects for green IoT application research.
Preface to the Proceedings of Green-Aware AI 2024 Ceur Workshop Proceedings, 2025
Adaptive Sensitivity-Aware Differential Privacy Accounting for Federated Smart-Meter Theft Detection D Labate, D Thakur, G Fortino Big Data and Cognitive Computing 10 (4), 113 , 2026 2026
Federated continual learning meets digital twins: A survey on methods, intersections and perspectives M Savoia, D Annunziata, D Thakur, G Fortino, F Piccialli Neurocomputing, 133366 , 2026 2026 Citations: 3
Agentic ElderFedLearn: A Differential Privacy-Based Approach for Elderly Disease Prediction SA Khowaja, K Dev, D Thakur, G Fortino IEEE Transactions on Computational Social Systems , 2026 2026
Layer-wise Quantization in Green-Aware AI F Ikram, D Thakur, A Guzzo, G Fortino 2nd Workshop on Green-Aware Artificial Intelligence, 28th European … , 2026 2026 Citations: 1
Empirical Analysis of FedAvg, FedProx and SCAFFOLD for Heterogeneous Data Distributions F Ikram, D Thakur, A Guzzo, G Fortino 2026 1st International Conference on Innovations in Information and … , 2026 2026
Exploring Process Mining in Human Activity Recognition: Challenges and Future Directions D Thakur, A Guzzo, G Fortino Internet of Things Meets Business Process Management: A Synergistic … , 2026 2026
GRACE-FL: Green Resource-Aware Communication-Efficient Federated Learning D Thakur, A Guzzo, G Fortino, SK Das IEEE Transactions on Artificial Intelligence , 2025 2025 Citations: 1
Quantization in Energy-Efficient Federated Learning F Ikram, D Thakur, A Guzzo, G Fortino 2025 International Joint Conference on Neural Networks (IJCNN), Rome, Italy, 1-7 , 2025 2025
EAPD-CS: Energy Aware Performance Driven Client Selection in Federated Learning based Human Activity Recognition * D Thakur, A Guzzo, G Fortino 2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC … , 2025 2025
Leveraging Cross-Silo Federated Learning in Process Mining [Short Paper] D Thakur, A Guzzo, G Fortino International Workshop on Leveraging Machine Learning in Process Mining … , 2025 2025
Anomalous Client Detection in Federated D Thakur, A Guzzo Intelligent Distributed Computing XVII: 17th International Symposium on … , 2025 2025
Analyzing the Fusion of Federated Learning and Large Language Model D Thakur, A Guzzo, G Fortino 2025 IEEE 5th International Conference on Human-Machine Systems (ICHMS), 282-288 , 2025 2025 Citations: 1
Green Federated Learning: A New Era of Green Aware AI D Thakur, A Guzzo, G Fortino, F Piccialli ACM Computing Surveys , 2025 2025 Citations: 67
Towards Secure and Scalable Energy Theft Detection: A Federated Learning Approach for Resource-Constrained Smart Meters D Labate, D Thakur, G Fortino IEEE Smart World Congress 2025, August 18 - 22, 2025, Calgary, Alberta, Canada , 2025 2025 Citations: 1
Preface to the Proceedings of Green-Aware AI 2024 R Cantini, DM Longo, D Thakur CEUR WORKSHOP PROCEEDINGS 3934 , 2025 2025
Multi-modal disease segmentation with continual learning and adaptive decision fusion X Xu, J Chen, D Thakur, D Hong Information Fusion 102962 , 2025 2025 Citations: 15
Client Specific Dynamic Aggregation for Non-IID Federated Learning V Altomare, D Thakur, A Guzzo, F Piccialli 2024 IEEE International Conference on Big Data (BigData), Washington, DC … , 2025 2025 Citations: 5
Non-Convex Optimization in Federated Learning via Variance Reduction and Adaptive Learning D Thakur, A Guzzo, G Fortino, SK Das arXiv preprint arXiv:2412.11660 , 2024 2024 Citations: 2
Intelligent adaptive real-time monitoring and recognition system for human activities D Thakur, A Guzzo, G Fortino IEEE Transactions on Industrial Informatics 20 (11), 13212-13222 , 2024 2024 Citations: 23
Hardware-algorithm co-design of energy efficient federated learning in quantized neural network D Thakur, A Guzzo, G Fortino Internet of Things 26, 101223 , 2024 2024 Citations: 12
MOST CITED SCHOLAR PUBLICATIONS
Convae-lstm: Convolutional autoencoder long short-term memory network for smartphone-based human activity recognition D Thakur, S Biswas, ESL Ho, S Chattopadhyay IEEE Access 10, 4137-4156 , 2022 2022 Citations: 114
Smartphone based human activity monitoring and recognition using ML and DL: a comprehensive survey D Thakur, S Biswas Journal of Ambient Intelligence and Humanized Computing , 2020 2020 Citations: 71
Green Federated Learning: A New Era of Green Aware AI D Thakur, A Guzzo, G Fortino, F Piccialli ACM Computing Surveys , 2025 2025 Citations: 67
An Integration of feature extraction and Guided Regularized Random Forest feature selection for Smartphone based Human Activity Recognition D Thakur, S Biswas Journal of Network and Computer Applications 204 (103417) , 2022 2022 Citations: 59
Permutation importance based modified guided regularized random forest in human activity recognition with smartphone D Thakur, S Biswas Engineering Applications of Artificial Intelligence 129, 107681 , 2024 2024 Citations: 57
Feature fusion using deep learning for smartphone based human activity recognition D Thakur, S Biswas International Journal of Information Technology , 2021 2021 Citations: 56
Attention-based multihead deep learning framework for online activity monitoring with smartwatch sensors D Thakur, A Guzzo, G Fortino IEEE Internet of Things Journal 10 (20), 17746-17754 , 2023 2023 Citations: 44
Guided regularized random forest feature selection for smartphone based human activity recognition D Thakur, S Biswas Journal of Ambient Intelligence and Humanized Computing 14 (7), 9767-9779 , 2023 2023 Citations: 37
Attention-based deep learning framework for hemiplegic gait prediction with smartphone sensors D Thakur, S Biswas IEEE Sensors Journal 22 (12), 11979-11988 , 2022 2022 Citations: 26
Intelligent adaptive real-time monitoring and recognition system for human activities D Thakur, A Guzzo, G Fortino IEEE Transactions on Industrial Informatics 20 (11), 13212-13222 , 2024 2024 Citations: 23
A Novel Smartphone-Based Human Activity Recognition Approach using Convolutional Autoencoder Long Short-Term Memory Network D Thakur, S Roy, S Biswas, ESL Ho, S Chattopadhyay, S Shetty 24th International Conference on Information Reuse and Integration for Data … , 2023 2023 Citations: 22
Online change point detection in application with transition-aware activity recognition D Thakur, S Biswas IEEE Transactions on Human-Machine Systems 52 (6), 1176-1185 , 2022 2022 Citations: 17
Load balancing in software defined network P Kumari, D Thakur International Journal of Computer Sciences and Engineering 5 (12), 227-232 , 2017 2017 Citations: 17
Multi-modal disease segmentation with continual learning and adaptive decision fusion X Xu, J Chen, D Thakur, D Hong Information Fusion 102962 , 2025 2025 Citations: 15
Hardware-algorithm co-design of energy efficient federated learning in quantized neural network D Thakur, A Guzzo, G Fortino Internet of Things 26, 101223 , 2024 2024 Citations: 12
t-SNE and PCA in ensemble learning based human activity recognition with smartwatch D Thakur, A Guzzo, G Fortino 2021 IEEE 2nd International Conference on Human-Machine Systems (ICHMS), 1-6 , 2021 2021 Citations: 12
Multi-domain virtual network embedding with dynamic flow migration in software-defined networks D Thakur, M Khatua Journal of Network and Computer Applications 162, 102639 , 2020 2020 Citations: 12
Human activity recognition: trends and challenges D Thakur, A Pal Activity Recognition and Prediction for Smart IoT Environments, 161-182 , 2024 2024 Citations: 6
Subsampled randomized hadamard transformation-based ensemble extreme learning machine for human activity recognition D Thakur, A Pal ACM Transactions on Computing for Healthcare 5 (1), 1-23 , 2024 2024 Citations: 6
Energy Aware Federated Learning with Application of Activity Recognition D Thakur, A Guzzo, G Fortino 2023 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf … , 2023 2023 Citations: 6
