Search Results (1,773)

The uneven expansion of renewable energy generation in different regions highlights the necessity of accurately assessing the available transfer capability (ATC) in power systems. This paper proposes a distributed probabilistic inter-regional ATC assessment framework. First, a spatiotemporally correlated wind power output model is established using wind speed forecast data and correlation matrices, enhancing the accuracy of wind power forecasting. Second, a two-stage probabilistic ATC assessment optimization model is proposed. The first stage minimizes both generation cost and risk-related costs by incorporating conditional value-at-risk (CVaR), while the second stage maximizes the power transaction amount. Thirdly, a privacy-preserving two-level iterative alternating direction method of multipliers (I-ADMM) algorithm is designed to solve this mixed-integer optimization problem, requiring only the exchange of boundary voltage phase angles between regions. Case studies are performed on the 12-bus, the IEEE 39-bus and the IEEE 118-bus systems to validate the proposed framework. Hence, the proposed framework enables more reliable and risk-aware intraday ATC evaluation for inter-regional power transactions. Moreover, the impacts of risk parameters and wind farm output correlations on ATC and generation cost are further investigated. Full article

This paper focuses on the efficient fine-tuning of large language models within the federated learning framework. To address the performance bottlenecks caused by multi-source heterogeneity and structural inconsistency, a structure-aware federated fine-tuning method is proposed. The method incorporates a graph representation module (GRM) to model internal structural relationships within text and employs a segmentation mechanism (SM) to reconstruct and align semantic structures across inputs, thereby enhancing structural robustness and generalization under non-IID (non-Independent and Identically Distributed) settings. During training, the method ensures data locality and integrates structural pruning with gradient encryption (SPGE) strategies to balance privacy preservation and communication efficiency. Compared with representative federated fine-tuning baselines such as FedNLP and FedPrompt, the proposed method achieves consistent accuracy and F1-score improvements across multiple tasks. To evaluate the effectiveness of the proposed method, extensive comparative experiments are conducted across tasks of text classification, named entity recognition, and question answering, using multiple datasets with diverse structures and heterogeneity levels. Experimental results show that the proposed approach significantly outperforms existing federated fine-tuning strategies on most tasks, achieving higher performance while preserving privacy, and demonstrating strong practical applicability and generalization potential. Full article

“Hiding in Plain Sight” (HIPS) strategies for Personal Health Information (PHI) replace PHI with surrogate values to hinder re-identification attempts. We evaluate three different HIPS strategies for PHI replacement, a standard Consistent replacement strategy, a Random replacement strategy, and a novel Markov model strategy. We evaluate the privacy-preserving benefits and relative utility for information extraction of these strategies on both a simulated PHI distribution and real clinical corpora from two different institutions using a range of false negative error rates (FNER). The Markov strategy consistently outperformed the Consistent and Random substitution strategies on both real data and in statistical simulations. Using FNER ranging from 0.1% to 5%, PHI leakage at the document level could be reduced from 27.1% to 0.1% and from 94.2% to 57.7% with the Markov strategy versus the standard Consistent substitution strategy, at 0.1% and 0.5% FNER, respectively. Additionally, we assessed the generated corpora containing synthetic PHI for reuse using a variety of information extraction methods. Results indicate that modern deep learning methods have similar performance on all strategies, but older machine learning techniques can suffer from the change in context. Overall, a Markov surrogate generation strategy substantially reduces the chance of inadvertent PHI release. Full article

Background: Neuroimaging-based diagnostic approaches are of critical importance for the accurate diagnosis and treatment of major depressive disorder (MDD). However, multisite neuroimaging data often exhibit substantial heterogeneity in terms of scanner protocols and population characteristics. Moreover, concerns over data ownership, security, and privacy make raw MRI datasets from multiple sites inaccessible, posing significant challenges to the development of robust diagnostic models. Federated learning (FL) offers a privacy-preserving solution to facilitate collaborative model training across sites without sharing raw data. Methods: In this study, we propose the personalized Federated Gradient Matching and Contrastive Optimization (pF-GMCO) algorithm to address domain shift and support scalable MDD classification using multimodal MRI. Our method incorporates gradient matching based on cosine similarity to weight contributions from different sites adaptively, contrastive learning to promote client-specific model optimization, and multimodal compact bilinear (MCB) pooling to effectively integrate structural MRI (sMRI) and functional MRI (fMRI) features. Results and Conclusions: Evaluated on the Rest-Meta-MDD dataset with 2293 subjects from 23 sites, pF-GMCO achieved accuracy of 79.07%, demonstrating superior performance and interpretability. This work provides an effective and privacy-aware framework for multisite MDD diagnosis using federated learning. Full article

In this paper, the use of nilpotent Lie algebras as the basis for homomorphic encryption based on additive operations is explored. The $g$-setting is set up over $g{l}_n\left({\mathbb{Z}}_q\right)$) and the group $G=exp\left(g\right)$, and it is noted that the exponential and logarithm series are truncated by nilpotency in a natural way. From this, an additive symmetric conjugation scheme is constructed: given a message element $M$ and a central randomizer $U\in z\left(g\right),$ we encrypt $=Kexp\left(M+U\right)K^{-1}$ and decrypt to $M=log\left(K^{-1}CK\right)-U$. The scheme is additive in nature, with the security defined in the IND-CPA model. Integrity is ensured using an encrypt-then-MAC construction. These properties together provide both confidentiality and robustness while preserving the homomorphic functionality. The scheme realizes additive homomorphism through a truncated BCH-sum, so it is suitable for ciphertext summations. We implemented a prototype and took reproducible measurements (Python 3.11/NumPy) of the series $\{{10,10}^2,{10}^3,{10}^4,{10}^5\}$ over 10 iterations, reporting the medians and 95% confidence intervals. The graphs exhibit that the latency per operation remains constant at fixed values, and the total time scales approximately linearly with the batch size; we also report the throughput, peak memory usage, $\mid C\mid /\mid M\mid$ expansion rate, and achievable aggregation depth. The applications are federated reporting, IoT telemetry, and privacy-preserving aggregations in DBMS; the limitations include its additive nature (lacking general multiplicative homomorphism), IND-CPA (but not CCA), and side-channel resistance requirements. We place our approach in contrast to the standard FHE building blocks BFV/BGV/CKKS nd the emerging NIST PQC standards (FIPS 203/204/205), as a well-established security model with future engineering optimizations. Full article

Automatic speech recognition (ASR) has advanced rapidly, evolving from early template-matching systems to modern deep learning frameworks. This review systematically traces ASR’s technological evolution across four phases: the template-based era, statistical modeling approaches, the deep learning revolution, and the emergence of large-scale models under diverse learning paradigms. We analyze core technologies such as hidden Markov models (HMMs), Gaussian mixture models (GMMs), recurrent neural networks (RNNs), and recent architectures including Transformer-based models and Wav2Vec 2.0. Beyond algorithmic development, we examine how ASR integrates into intelligent information systems, analyzing real-world applications in healthcare, education, smart homes, enterprise systems, and automotive domains with attention to deployment considerations and system design. We also address persistent challenges—noise robustness, low-resource adaptation, and deployment efficiency—while exploring emerging solutions such as multimodal fusion, privacy-preserving modeling, and lightweight architectures. Finally, we outline future research directions to guide the development of robust, scalable, and intelligent ASR systems for complex, evolving environments. Full article

Current medical informatics systems face critical challenges, including limited scalability across distributed institutions, insufficient real-time AI-driven decision support, and lack of standardized interoperability for heterogeneous medical data exchange. To address these challenges, this paper proposes a novel distributed web system architecture for medical informatics, integrating artificial intelligence techniques and cloud-based services. The system ensures interoperability via HL7 FHIR standards and preserves data privacy and fault tolerance across interconnected medical institutions. A hybrid AI pipeline combining principal component analysis (PCA), K-Means clustering, and convolutional neural networks (CNNs) is applied to diffusion tensor imaging (DTI) data for early detection of neurological anomalies. The architecture leverages containerized microservices orchestrated with Docker Swarm, enabling adaptive resource management and high availability. Experimental validation confirms reduced latency, improved system reliability, and enhanced compliance with medical data exchange protocols. Results demonstrate superior performance with an average latency of 94 ms, a diagnostic accuracy of 91.3%, and enhanced clinical workflow efficiency compared to traditional monolithic architectures. The proposed solution successfully addresses scalability limitations while maintaining data security and regulatory compliance across multi-institutional deployments. This work contributes to the advancement of intelligent, interoperable, and scalable e-health infrastructures aligned with the evolution of digital healthcare ecosystems. Full article

The General Data Protection Regulation (GDPR) imposes additional demands and obligations on service providers that handle and process personal data. In this paper, we examine how advanced cryptographic techniques can be employed to develop a privacy-preserving solution for ensuring GDPR compliance in Industrial Internet of Things (IIoT) systems. The primary objective is to ensure that sensitive data from IIoT devices is encrypted and accessible only to authorized entities, in accordance with Article 32 of the GDPR. The proposed system combines Decentralized Attribute-Based Encryption (DABE) with smart contracts on a blockchain to create a decentralized way of managing access to IIoT systems. The proposed system is used in an IIoT use case where industrial sensors collect operational data that is encrypted according to DABE. The encrypted data is stored in the IPFS decentralized storage system. The access policy and IPFS hash are stored in the blockchain’s smart contracts, allowing only authorized and compliant entities to retrieve the data based on matching attributes. This decentralized system ensures that information is stored encrypted and secure until it is retrieved by legitimate entities, whose access rights are automatically enforced by smart contracts. The implementation and evaluation of the proposed system have been analyzed and discussed, showing the promising achievement of the proposed system. Full article

The increasing use of AI systems for face, object, action, scene, and emotion recognition raises significant privacy risks, particularly when processing Personally Identifiable Information (PII). Current privacy-preserving methods lack adaptability to users’ preferences and contextual requirements, and obfuscate user faces uniformly. This research proposes a user-centric, context-aware, and ontology-driven privacy protection framework that dynamically adjusts privacy decisions based on user-defined preferences, entity sensitivity, and contextual information. The framework integrates state-of-the-art recognition models for recognising faces, objects, scenes, actions, and emotions in real time on data acquired from vision sensors (e.g., cameras). Privacy decisions are directed by a contextual ontology based in Contextual Integrity theory, which classifies entities into private, semi-private, or public categories. Adaptive privacy levels are enforced through obfuscation techniques and a multi-level privacy model that supports user-defined red lines (e.g., “always hide logos”). The framework also proposes a Re-Identifiability Index (RII) using soft biometric features such as gait, hairstyle, clothing, skin tone, age, and gender, to mitigate identity leakage and to support fallback protection when face recognition fails. The experimental evaluation relied on sensor-captured datasets, which replicate real-world image sensors such as surveillance cameras. User studies confirmed that the framework was effective, with over 85.2% of participants rating the obfuscation operations as highly effective, and the other 14.8% stating that obfuscation was adequately effective. Amongst these, 71.4% considered the balance between privacy protection and usability very satisfactory and 28% found it satisfactory. GPU acceleration was deployed to enable real-time performance of these models by reducing frame processing time from 1200 ms (CPU) to 198 ms. This ontology-driven framework employs user-defined red lines, contextual reasoning, and dual metrics (RII/IVI) to dynamically balance privacy protection with scene intelligibility. Unlike current anonymisation methods, the framework provides a real-time, user-centric, and GDPR-compliant method that operationalises privacy-by-design while preserving scene intelligibility. These features make the framework appropriate to a variety of real-world applications including healthcare, surveillance, and social media. Full article

The Attribute-Based Access Control (ABAC) model provides access control decisions based on subject, object (resource), and contextual attributes. However, the use of sensitive attributes in access control decisions poses many security and privacy challenges, particularly in cloud environment where third parties are involved. To address this shortcoming, we present a novel privacy-preserving Dummy-ABAC model that obfuscates real attributes with dummy attributes before transmission to the cloud server. In the proposed model, only dummy attributes are stored in the cloud database, whereas real attributes and mapping tokens are stored in a local machine database. Only dummy attributes are used for the access request evaluation in the cloud, and real data are retrieved in the post-decision mechanism using secure tokens. The security of the proposed model was assessed using a simulated threat scenario, including attribute inference, policy injection, and reverse mapping attacks. Experimental evaluation using machine learning classifiers (“DecisionTree” DT, “RandomForest” RF), demonstrated that inference accuracy dropped from ~0.65 on real attributes to ~0.25 on dummy attributes confirming improved resistance to inference attacks. Furthermore, the model rejects malformed and unauthorized policies. Performance analysis of dummy generation, token generation, encoding, and nearest-neighbor search, demonstrated minimal latency in both local and cloud environments. Overall, the proposed model ensures an efficient, secure, and privacy-preserving access control in cloud environments. Full article

A personalized framework for smart home automation is introduced, utilizing machine learning to predict user activities and allow for the context-aware control of living spaces. Predicting user activities, such as ‘Watch_TV’, ‘Sleep’, ‘Work_On_Computer’, and ‘Cook_Dinner’, is essential for improving occupant comfort, optimizing energy consumption, and offering proactive support in smart home settings. The Edge Light Human Activity Recognition Predictor, or EL-HARP, is the main prediction model used in this framework to predict user behavior. The system combines open-source software for real-time sensing, facial recognition, and appliance control with affordable hardware, including the Raspberry Pi 5, ESP32-CAM, Tuya smart switches, NFC (Near Field Communication), and ultrasonic sensors. In order to predict daily user activities, three gradient-boosting models—XGBoost, CatBoost, and LightGBM (Gradient Boosting Models)—are trained for each household using engineered features and past behaviour patterns. Using extended temporal features, LightGBM in particular achieves strong predictive performance within EL-HARP. The framework is optimized for edge deployment with efficient training, regularization, and class imbalance handling. A fully functional prototype demonstrates real-time performance and adaptability to individual behavior patterns. This work contributes a scalable, privacy-preserving, and user-centric approach to intelligent home automation. Full article

Natural disasters can disrupt communication services, leading to severe consequences in emergencies. Maintaining connectivity and communication quality during crises is crucial for coordinating rescues, providing critical information, and ensuring reliable and secure service. This study proposes FedResilience, a Federated Learning (FL) system for classifying Long-Term Evolution (LTE) network coverage in both normal operation and natural disaster scenarios. A three-tier architecture is implemented: (i) edge nodes, (ii) a central aggregation server, and (iii) a batch processing interface. Five FL aggregation methods (FedAvg, FedProx, FedAdam, FedYogi, and FedAdagrad) were evaluated under normal conditions and disaster simulations. The results show that FedAdam outperforms the other methods under normal conditions, achieving an F1 score of 0.7271 and a Global System Adherence ($S{A}_{\mathrm{global}}$) of 91.51%. In disaster scenarios, FedProx was superior, with an F1 score of 0.7946 and $S{A}_{\mathrm{global}}$ of 61.73%. The innovation in this study is the introduction of the System Adherence (SA) metric to evaluate the predictive fidelity of the model. The system demonstrated robustness against Non-Independent and Identically Distributed (non-IID) data distributions and the ability to handle significant class imbalances. FedResilience serves as a tool for companies to implement automated corrective actions, contributing to the predictive maintenance of LTE networks through FL while preserving data privacy. Full article

We propose an edge-enhanced federated learning framework for real-time itinerary optimization in elderly oriented adventure tourism, addressing the critical need for adaptive scheduling that balances activity intensity with health constraints. The system integrates lightweight convolutional neural networks with a priority-based scheduling algorithm, processing participant profiles and real-time biometric data through a decentralized computation model to enable dynamic adjustments. A modified Hungarian algorithm incorporates physical exertion scores, temporal proximity weights, and health risk factors, then optimizes activity assignments while respecting physiological recovery requirements. The federated learning architecture operates across distributed edge nodes, preserving data privacy through localized model training and periodic global aggregation. Furthermore, the framework interfaces with transportation systems and medical monitoring infrastructure, automatically triggering itinerary modifications when vital sign anomalies exceed adaptive thresholds. Implemented on NVIDIA Jetson AGX Orin modules, the system achieves 300 ms end-to-end latency for real-time schedule updates, meeting stringent safety requirements for elderly participants. The proposed method demonstrates significant improvements over conventional itinerary planners through its edge computing efficiency and personalized adaptation capabilities, particularly in handling the latency-sensitive demands of intensive tourism scenarios. Experimental results show robust performance across diverse participant profiles and activity types, confirming the system’s practical viability for real-world deployment in elderly adventure tourism operations. Full article

As more machine learning models are used in sensitive fields like healthcare, finance, and smart infrastructure, protecting structured tabular data from privacy attacks is a key research challenge. Although several privacy-preserving methods have been proposed for tabular data, a comprehensive comparison of their performance and trade-offs has yet to be conducted. We introduce and empirically assess a combined defense system that integrates differential privacy, federated learning, adaptive noise injection, hybrid cryptographic encryption, and ensemble-based obfuscation. The given strategies are analyzed on the benchmark tabular datasets (ADULT, GSS, FTE), showing that the suggested methods can mitigate up to 50 percent of model inversion attacks in relation to baseline models without decreasing the model utility (F1 scores are higher than 0.85). Moreover, on these datasets, our results match or exceed the latest state-of-the-art (SOTA) in terms of privacy. We also transform each defense into essential data privacy laws worldwide (GDPR and HIPAA), suggesting the best applicable guidelines for the ethical and regulation-sensitive deployment of privacy-preserving machine learning models in sensitive spaces. Full article

In quantum key distribution (QKD), public discussion over the authenticated classical channel inevitably leaks information about the raw key to a potential adversary, which must later be mitigated by privacy amplification. To limit this leakage, a one-time pad (OTP) has been proposed to protect message exchanges in various settings. Building on the security proof of Tomamichel and Leverrier, which is based on a non-asymptotic framework and considers the effects of finite resources, we extend the analysis to the OTP-protected scheme. We show that when the OTP key is drawn from the entropy pool of the same QKD session, the achievable quantum key rate is identical to that of the reference protocol with unprotected error-correction exchange. This equivalence holds for a fixed security level, defined via the diamond distance between the real and ideal protocols modeled as completely positive trace-preserving maps. At the same time, the proposed approach reduces the computational requirements: for non-interactive low-density parity-check codes, the encoding problem size is reduced by the square of the syndrome length, while privacy amplification requires less compression. The technique preserves security, avoids the use of QKD keys between sessions, and has the potential to improve performance. Full article