Search Results (1,392)

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

In today’s digital era, cyberattacks are rapidly evolving, rendering traditional security mechanisms increasingly inadequate. The adoption of AI-based Network Intrusion Detection Systems (NIDS) has emerged as a promising solution, due to their ability to detect and respond to malicious activity using machine learning techniques. However, these systems remain vulnerable to adversarial threats, particularly data poisoning attacks, in which attackers manipulate training data to degrade model performance. In this work, we examine tree classifiers, Random Forest and Gradient Boosting, to model black box poisoning attacks. We introduce FortiNIDS, a robust framework that employs a surrogate neural network to generate adversarial perturbations that can transfer between models, leveraging the transferability of adversarial examples. In addition, we investigate defense strategies designed to improve the resilience of NIDS in smart city Internet of Things (IoT) settings. Specifically, we evaluate adversarial training and the Reject on Negative Impact (RONI) technique using the widely adopted CICDDoS2019 dataset. Our findings highlight the effectiveness of targeted defenses in improving detection accuracy and maintaining system reliability under adversarial conditions, thereby contributing to the security and privacy of smart city networks. Full article

Modern cybersecurity threats continue to evolve in both complexity and prevalence, demanding advanced solutions for intrusion detection. Traditional AI-based detection systems face significant challenges in model selection, as performance varies considerably across different network environments and attack scenarios. To overcome these limitations, we propose a comprehensive ensemble learning approach that systematically integrates feature selection, model optimization, and rigorous evaluation components. Our framework evaluates fourteen distinct machine learning approaches, ranging from individual classifiers to sophisticated ensemble methods including bagging, boosting, and hybrid stacking/blending architectures. These techniques are applied to multiple base algorithms such as neural networks and tree-based models. Extensive testing was conducted on two complementary benchmark datasets (RoEduNet-SIMARGL2021 and CICIDS-2017) to assess detection capabilities across varied threat landscapes. Our experimental results revealed several key findings. Ensemble techniques universally surpass standalone models in detection accuracy, with random forest achieving the best performance on RoEduNet-SIMARGL2021, while the blending and bagging methods approach yielded perfect scores (F1 > 0.996) on CICIDS-2017. Feature selection via information gain demonstrated particular value, reducing model training times by 94% while maintaining detection accuracy. Among ensemble methods, XGBoost showed exceptional computational efficiency, whereas stacking and blending architectures delivered maximum accuracy at the expense of greater resource requirements. This research provides practical guidance for security professionals in model selection based on specific operational constraints and threat profiles. To support community advancement, we have made our complete framework publicly available, facilitating reproducibility and future innovation in intrusion detection systems. Full article

In the context of the new power system, high-current switchgear is prone to various faults due to complex operation environments and severe load fluctuations. Among them, an abnormal temperature rise can lead to contact oxidation, insulation aging, and even equipment failure, posing a serious threat to the safety of the distribution system. The operation risk assessment of high-current switchgear has thus become a key to ensuring the safety of the distribution system. Ensemble learning, which integrates the advantages of multiple models, provides an effective approach for accurate and intelligent risk assessment. However, existing ensemble learning methods have shortcomings in feature extraction, time-series modeling, and generalization ability. Therefore, this paper first preprocesses and reduces the dimensionality of multi-source data, such as historical load and equipment operation status. Secondly, we propose an operation risk assessment method for high-current switchgear based on ensemble learning: in the first layer, an improved random forest (RF) is used to optimize feature extraction; in the second layer, an improved long short-term memory (LSTM) network with an attention mechanism is adopted to capture time-series dependent features; in the third layer, an adaptive back propagation neural network (ABPNN) model fused with an adaptive genetic algorithm is utilized to correct the previous results, improving the stability of the assessment. Simulation results show that in temperature rise prediction, the proposed algorithm significantly improves the goodness-of-fit indicator with increases of 15.4%, 4.9%, and 24.8% compared to three baseline algorithms, respectively. It can accurately assess the operation risk of switchgear, providing technical support for intelligent equipment operation and maintenance, and safe operation of the system. Full article

The escalating consequences of human activities and global warming have markedly increased the frequency and intensity of geological disasters worldwide, posing a formidable threat to human life and property. In the southern mountainous region of Ningxia, China—an area characterized by complex topography, interlaced ravines, and pronounced ecological fragility—recurrent geological disasters have substantially constrained rural revitalization and development. This study introduces the integration of the Information Value (IV) method with Random Forest (RF) and XGBoost models, identifying IV + XGBoost as the optimal model through rigorous ROC-curve validation. The results reveal that low- and lower-risk areas account for 58.63% of the total area (7644.20 km² and 4038.08 km²), medium-risk areas cover 29.24% (5825.76 km²), and high-risk regions constitute 12.13% (2417.28 km²). The latter are predominantly in river valleys with high population density and intensive economic activities. These findings provide practical recommendations for scientifically informed disaster management and decision-making by relevant authorities. Furthermore, the proposed methodology offers valuable insights for disaster risk assessment in other regions with similar complex terrains and ecological vulnerabilities, contributing to developing more effective and sustainable disaster mitigation strategies. Full article

Pine wilt disease (PWD), transmitted by Monochamus alternatus (JPS), poses a severe threat to global pine forests. Although the entomopathogenic fungi Beauveria bassiana (Bb) and Metarhizium anisopliae (Ma) represent environmentally friendly biocontrol alternatives, their practical application is limited by inconsistent field performance and an incomplete understanding of host–pathogen interactions. We employed dual RNA-seq at the critical 48 h infection time point to systematically compare the transcriptional responses between JPS and Bb/Ma during infection. Key findings revealed distinct infection strategies: Bb preferentially induced autophagy pathways and modulated host carbohydrate metabolism to facilitate nutrient acquisition, triggering corresponding tissue degradation responses in JPS. In contrast, Ma primarily co-opted host amino acid and sugar metabolic pathways for biosynthetic processes, eliciting a stronger immune defense activation in JPS. Notably, the mTOR signaling pathway was identified as a key regulator of the differential host responses to various entomopathogenic fungi. Further functional validation-specifically, the application of a chemical inhibitor and RNAi targeting mTOR in JPS-confirmed that mTOR inhibition selectively enhanced Bb-induced mortality in JPS without affecting Ma virulence. Our findings reveal the molecular determinants of host–pathogen specificity in PWD biological control and indicate that mTOR regulation could serve as an effective strategy to improve fungal pesticide performance. Full article

The burgeoning Internet of Medical Things (IoMT) offers unprecedented opportunities for real-time patient monitoring and predictive diagnostics, yet the current systems struggle with scalability, data confidentiality against quantum threats, and real-time privacy-preserving intelligence. This paper introduces Med-Q Ledger, a novel, multi-layered framework designed to overcome these critical limitations in the Medical IoT domain. Med-Q Ledger integrates a permissioned Hyperledger Fabric for transactional integrity with a scalable Holochain Distributed Hash Table for high-volume telemetry, achieving horizontal scalability and sub-second commit times. To fortify long-term data security, the framework incorporates post-quantum cryptography (PQC), specifically CRYSTALS-Di lithium signatures and Kyber Key Encapsulation Mechanisms. Real-time, privacy-preserving intelligence is delivered through an edge-based federated learning (FL) model, utilizing lightweight autoencoders for anomaly detection on encrypted gradients. We validate Med-Q Ledger’s efficacy through a critical application: the prediction of intestinal complications like necrotizing enterocolitis (NEC) in preterm infants, a condition frequently necessitating emergency colostomy. By processing physiological data from maternal wearable sensors and infant intestinal images, our integrated Random Forest model demonstrates superior performance in predicting colostomy necessity. Experimental evaluations reveal a throughput of approximately 3400 transactions per second (TPS) with ~180 ms end-to-end latency, a >95% anomaly detection rate with <2% false positives, and an 11% computational overhead for PQC on resource-constrained devices. Furthermore, our results show a 0.90 F1-score for colostomy prediction, a 25% reduction in emergency surgeries, and 31% lower energy consumption compared to MQTT baselines. Med-Q Ledger sets a new benchmark for secure, high-performance, and privacy-preserving IoMT analytics, offering a robust blueprint for next-generation healthcare deployments. Full article

Wheat, a globally vital food crop, faces severe threats from numerous foliar diseases, which often infect agricultural fields, significantly compromising yield and quality. Rapid and accurate identification of the specific disease is crucial for ensuring food security. Although progress has been made in wheat foliar disease detection using RGB imaging and spectroscopy, most prior studies have focused on identifying the presence of a single disease, without considering the need to operationalize such methods, and it will be necessary to differentiate between multiple diseases. In this study, we systematically investigate the differentiation of three wheat foliar diseases (e.g., powdery mildew, stripe rust, and leaf rust) and evaluate feature selection strategies and machine learning models for disease identification. Based on field experiments conducted from 2017 to 2024 employing artificial inoculation, we established a standardized hyperspectral database of wheat foliar diseases classified by disease severity. Four feature selection methods were employed to extract spectral features prior to classification: continuous wavelet projection algorithm (CWPA), continuous wavelet analysis (CWA), successive projections algorithm (SPA), and Relief-F. The selected features (which are derived by CWPA, CWA, SPA, and Relief-F algorithm) were then used as predictors for three disease-identification machine learning models: random forest (RF), k-nearest neighbors (KNN), and naïve Bayes (BAYES). Results showed that CWPA outperformed other feature selection methods. The combination of CWPA and KNN for discriminating disease-infected (powdery mildew, stripe rust, leaf rust) and healthy leaves by using only two key features (i.e., 668 nm at wavelet scale 5 and 894 nm at wavelet scale 7), achieved an overall accuracy (OA) of 77% and a map-level image classification efficacy (MICE) of 0.63. This combination of feature selection and machine learning model provides an efficient and precise procedure for discriminating between multiple foliar diseases in agricultural fields, thus offering technical support for precision agriculture. Full article

Phishing emails remain a significant concern and a growing cybersecurity threat in online communication. They often bypass traditional filters due to their increasing sophistication. This study presents a comparative evaluation of machine learning (ML) models and transformer-based large language models (LLMs) for phishing email detection, with embedded URL analysis. This study assessed ML training and LLM fine-tuning on both balanced and imbalanced datasets. We evaluated multiple ML models, including Random Forest, Logistic Regression, Support Vector Machine, Naïve Bayes, Gradient Boosting, Decision Tree, and K-Nearest Neighbors, alongside transformer-based LLMs DistilBERT, ALBERT, BERT-Tiny, ELECTRA, MiniLM, and RoBERTa. To further enhance realism, phishing emails generated by LLMs were included in the evaluation. Across all configurations, both the ML models and the fine-tuned LLMs demonstrated robust performance. Random Forest achieved over 98% accuracy in both email detection and URL classification. DistilBERT obtained almost as high scores on emails and URLs. Balancing the dataset led to slight accuracy gains in ML models but minor decreases in LLMs, likely due to their sensitivity to majority class reductions during training. Overall, LLMs are highly effective at capturing complex language patterns, while traditional ML models remain efficient and require low computational resources. Combining both approaches through a hybrid or ensemble method could enhance phishing detection effectiveness. Full article

The European spruce bark beetle, Ips typographus (Linnaeus, 1758), poses a significant threat to Picea abies (Linnaeus) Karsten, 1881 forests, with outbreaks often exacerbated by abiotic disturbances like the 2018 Vaia windstorm in the Italian Alps. Pheromone-baited traps are widely used for control, yet their overall efficacy and potential side effects, particularly the incidental capture of non-target insects, remain debated. This study aimed to comprehensively assess the presence and composition of non-target insects in I. typographus pheromone traps, used for both mass-trapping and monitoring, in the affected Alpine regions. We took into account single monitoring traps (dry collection) and three-trap cross configurations for mass-trapping (with preservative liquid), collecting and morphologically identifying insect by-catch. Our results revealed a non-target proportion (excluding bark beetles) significantly higher in mass-trapping (4.15%) compared to monitoring (1.00%), with approximately half being natural enemies of bark beetles. Crucially, we report that bark beetle parasitoids were repeatedly caught, with Tomicobia seitneri (Ruschka, 1924) (the third most abundant non-target species) particularly well represented, and Ropalophorus clavicornis (Wesmaël, 1835) also detected, which is noteworthy given its ecological role despite its lower numbers. Our findings underscore the significant, previously underreported, capture of beneficial parasitoids and highlight the need for careful consideration of non-target catches in I. typographus pest management strategies. Full article

The restoration of forest ecosystems damaged by wildfires and pest outbreaks has become increasingly urgent. However, the public-good nature of forests, the involvement of diverse stakeholders, and the spatial variability of degradation present significant challenges to effective policy design. In particular, previous studies have largely examined these threats in isolation, and few have provided integrated economic analyses of their combined impacts. This gap underscores the need to better understand heterogeneous public preferences and their implications for restoration policy. To address this, we conducted a discrete choice experiment (DCE) with 1021 Korean citizens and applied a two-stage analytical framework combining principal component analysis (PCA) and latent class choice modeling (LCM). Five distinct preference segments were identified, each exhibiting substantial variation in willingness to pay (WTP) for restoration attributes. Policy simulations further revealed that public acceptance declines sharply at higher cost levels, highlighting the importance of setting realistic financial thresholds for broad support. While visual materials, consequentiality checks, and cheap talk scripts were employed to mitigate hypothetical bias, the limitations of external validity and potential sampling biases should be acknowledged. Our findings provide empirical evidence for tailoring restoration policies to different stakeholder groups, while also stressing the financial and institutional constraints of implementation. In particular, the results suggest that cost thresholds, citizen engagement, and awareness-raising strategies must be carefully balanced to ensure both effectiveness and public acceptance. Taken together, these insights contribute to evidence-based forest policymaking that is both economically efficient and socially acceptable, while recognizing the context-specific limitations of the Korean case and the need for comparative studies across countries. Full article

Low-voltage series arc faults pose a significant threat to power system safety due to their random, nonlinear, and non-stationary characteristics. Traditional detection methods often suffer from low sensitivity and poor robustness under complex load conditions. To address these challenges, this paper proposes a novel detection framework based on Random Forest (RF) feature selection, Adaptive Boosting (Adaboost) classification, and SHapley Additive exPlanations (SHAP) interpretability. First, RF is employed to rank and select the most discriminative features from arc fault current signals. Then, the selected features are input into an Adaboost classifier to enhance the detection accuracy and generalization capability. Finally, SHAP values are introduced to quantify the contribution of each feature, improving the transparency and interpretability of the model. Experimental results on a self-built arc fault dataset demonstrate that the proposed method achieves an accuracy of 97.1%, outperforming five widely used traditional classifiers. The integration of SHAP further reveals the physical relevance of key features, providing valuable insights for practical applications. This study confirms that the proposed RF-Adaboost-SHAP framework offers both high accuracy and interpretability, making it suitable for real-time arc fault detection in complex load scenarios. Full article

The Republic of Korea, with 64% forest coverage, is increasingly vulnerable to large-scale wildfires. This study employed electrical resistance tomography (ERT) to diagnose internal damage in Pinus densiflora trees following a surface fire in spring 2023. Of the 30 monitored trees, 5 died in 2023 and 6 more had died by 2024. Dead trees showed a 41% higher Bark Scorch Index (BSI) and a 10%–15% lower DBH and circumference than survivors. From July, ERT detected significant increases in high- (ERT_R) and medium-resistance (ERT_Y) areas, while low-resistance (ERT_B) regions declined. By September, ERT_R and ERT_Y were 2.2 and 1.9 times higher in dead trees. Maximum resistivity (Rs_max) rose 6.1-fold to 3724 Ωm. One year post-fire, healthy areas in dead trees dropped below 18%. These findings indicate that internal defects develop gradually and accelerate in summer and winter, correlating with thermal and freeze–thaw stress. Early diagnosis within two months post-fire was unreliable, while post-summer assessments better distinguished trees at mortality risk. This study demonstrates ERT’s utility as a non-destructive tool for tracking post-fire damage and guiding forest restoration under increasing wildfire threats. Full article

Groundwater fluoride contamination poses a significant threat to sustainable water resources and public health, yet conventional water quality analysis is both time-consuming and costly, making large-scale, sustainable monitoring challenging. Machine learning methods offer a promising, cost-effective, and sustainable alternative for assessing the spatial distribution of fluoride. This study aimed to develop and compare the performance of Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN) models for predicting groundwater fluoride contamination in the Datong Basin with the help of satellite embeddings from the AlphaEarth Foundation. Data from 391 groundwater sampling points were utilized, with the dataset partitioned into training (80%) and testing (20%) sets. The ANOVA F-value of each feature was calculated for feature selection, identifying surface elevation, pollution, population, evaporation, vertical distance to the rivers, distance to the Sanggan river, and nine extra bands from the satellite embeddings as the most relevant input variables. Model performance was evaluated using the confusion matrix and the area under the receiver operating characteristic curve (ROC-AUC). The results showed that the SVM model demonstrated the highest ROC-AUC (0.82), outperforming the RF (0.80) and MLP (0.77) models. The introduction of satellite embeddings improved the performance of all three models significantly, with the prediction errors decreasing by 13.8% to 23.3%. The SVM model enhanced by satellite embeddings proved to be a robust and reliable tool for predicting groundwater fluoride contamination, highlighting its potential for use in sustainable groundwater management. Full article

Battery Energy Storage Systems (BESSs) are critical to smart grid functioning but are exposed to mounting cybersecurity threats with their integration into IoT and cloud-based control systems. Current solutions tend to be deficient in proper multi-class attack classification, secure encryption, and full integrity and power quality features. This paper proposes a comprehensive framework that integrates machine learning for attack detection, cryptographic security, data validation, and power quality control. With the BESS-Set dataset for binary classification, Random Forest achieves more than 98.50% accuracy, while LightGBM attains more than 97.60% accuracy for multi-class classification on the resampled data. Principal Component Analysis and feature importance show vital indicators such as State of Charge and battery power. Secure communication is implemented using Elliptic Curve Cryptography and a hybrid Blowfish–RSA encryption method. Data integrity is ensured through applying anomaly detection using Z-scores and redundancy testing, and IEEE 519-2022 power quality compliance is ensured by adaptive filtering and harmonic analysis. Real-time feasibility is demonstrated through hardware implementation on a PYNQ board, thus making this framework a stable and feasible option for BESS security in smart grids. Full article