Aqueous lead monosulfide(PbS)quantum dots(QDs)fabricated by conventional approaches display poor photodetection performance and unsatisfactory chemical stability,so various strategies for well-defined PbS QD-based het...Aqueous lead monosulfide(PbS)quantum dots(QDs)fabricated by conventional approaches display poor photodetection performance and unsatisfactory chemical stability,so various strategies for well-defined PbS QD-based heterostructures have been developed,which are usually complicated and unsuitable for largescale production.In this work,homogeneous ultrasmall,uniform ternary Pb_(1−x)Cd_(x)S QDs are rationally designed and successfully fabricated by an in situ aqueous coprecipitation method.展开更多
Kesterite Cu_(2)ZnSn(S,Se)_(4)(CZTSSe)is a promising candidate for photodetector(PD)applications thanks to its excellent optoelectronic properties.In this work,a green solution-processed spin coating and selenization-...Kesterite Cu_(2)ZnSn(S,Se)_(4)(CZTSSe)is a promising candidate for photodetector(PD)applications thanks to its excellent optoelectronic properties.In this work,a green solution-processed spin coating and selenization-processed thermodynamic or kinetic growth of high-quality narrow bandgap kesterite CZTSSe thin film is developed.A self-powered CZTSSe/CdS thin-film PD is then successfully fabricated.Under optimization of light absorber and heterojunction interface,especially tailoring the defect and carrier kinetics,it can achieve broadband response from300 to 1300 nm,accompaniedwith a high responsivity of 1.37A/W,specific detectivity(D*)up to 4.0×10^(14)Jones under 5 nW/cm^(2),a linear dynamic range(LDR)of 126 dB,and a maximum Ilight/Idark ratio of 1.3×10^(8)within the LDR,and ultrafast response speed(rise/decay time of 16 ns/85 ns),representing the leading-level performance to date,which is superior to those of commercial andwell-researched photodiodes.Additionally,an imaging system with a 905nm laser is built for weak light response evaluation,and can respond to 718 pW weak light and infrared imaging at a wavelength as low as 5 nW/cm2.It has also been employed for photoplethysmography detection of pulsating signals at both the finger and wrist,presenting obvious arterial blood volume changes,demonstrating great application potential in broadband and weak light photodetection scenarios.展开更多
Visible and infrared(RGB-IR)fusion object detection plays an important role in security,disaster relief,etc.In recent years,deep-learning-based RGB-IR fusion detection methods have been developing rapidly,but still st...Visible and infrared(RGB-IR)fusion object detection plays an important role in security,disaster relief,etc.In recent years,deep-learning-based RGB-IR fusion detection methods have been developing rapidly,but still struggle to deal with the complex and changing scenarios captured by drones,mainly due to two reasons:(A)RGB-IR fusion detectors are susceptible to inferior inputs that degrade performance and stability.(B)RGB-IR fusion detectors are susceptible to redundant features that reduce accuracy and efficiency.In this paper,an innovative RGB-IR fusion detection framework based on global-local feature optimization,named GLFDet,is proposed to improve the detection performance and efficiency of drone-captured objects.The key components of GLFDet include a Global Feature Optimization(GFO)module,a Local Feature Optimization(LFO)module and a Channel Separation Fusion(CSF)module.Specifically,GFO calculates the information content of the input image from the frequency domain and optimizes the features holistically.Then,LFO dynamically selects high-value features and filters out low-value features before fusion,which significantly improves the efficiency of fusion.Finally,CSF fuses the RGB and IR features across the corresponding channels,which avoids the rearrangement of the channel relationships and enhances the model stability.Extensive experimental results show that the proposed method achieves the best performance on three popular RGB-IR datasets Drone Vehicle,VEDAI,and LLVIP.In addition,GLFDet is more lightweight than other comparable models,making it more appealing to edge devices such as drones.The code is available at https://github.com/lao chen330/GLFDet.展开更多
Underwater pipeline inspection plays a vital role in the proactive maintenance and management of critical marine infrastructure and subaquatic systems.However,the inspection of underwater pipelines presents a challeng...Underwater pipeline inspection plays a vital role in the proactive maintenance and management of critical marine infrastructure and subaquatic systems.However,the inspection of underwater pipelines presents a challenge due to factors such as light scattering,absorption,restricted visibility,and ambient noise.The advancement of deep learning has introduced powerful techniques for processing large amounts of unstructured and imperfect data collected from underwater environments.This study evaluated the efficacy of the You Only Look Once(YOLO)algorithm,a real-time object detection and localization model based on convolutional neural networks,in identifying and classifying various types of pipeline defects in underwater settings.YOLOv8,the latest evolution in the YOLO family,integrates advanced capabilities,such as anchor-free detection,a cross-stage partial network backbone for efficient feature extraction,and a feature pyramid network+path aggregation network neck for robust multi-scale object detection,which make it particularly well-suited for complex underwater environments.Due to the lack of suitable open-access datasets for underwater pipeline defects,a custom dataset was captured using a remotely operated vehicle in a controlled environment.This application has the following assets available for use.Extensive experimentation demonstrated that YOLOv8 X-Large consistently outperformed other models in terms of pipe defect detection and classification and achieved a strong balance between precision and recall in identifying pipeline cracks,rust,corners,defective welds,flanges,tapes,and holes.This research establishes the baseline performance of YOLOv8 for underwater defect detection and showcases its potential to enhance the reliability and efficiency of pipeline inspection tasks in challenging underwater environments.展开更多
【Objective】This study aimed to establish a quintuple PCR method for rapid and simultaneous detection of Ralstonia solanacearum,Fusarium spp.,Pectobacterium spp.,Enterobacter spp.,and Pythium spp.,which provided tech...【Objective】This study aimed to establish a quintuple PCR method for rapid and simultaneous detection of Ralstonia solanacearum,Fusarium spp.,Pectobacterium spp.,Enterobacter spp.,and Pythium spp.,which provided technical support for early diagnosis of various soil-borne diseases on ginger.【Method】For five types of soil-borne pathogens causing ginger bacterial wilt and rhizome rot,specific primer combinations were designed and screened,the optimal quintuple reaction system was established by exploring optimal primer concentrations,annealing temperature,and sensitivity,and was applied to detect field plant samples to verify its utility.【Result】Specific primers pairs Rs1F/Rs1R,En1F/En1R,and Py1F/Py1R were designed according to flic gene of Ralstonia solanacearum,rpoB gene of Enterobacter spp.,and 18S rDNA of Pythium spp.,and combined with reported Fusarium spp.specific primers Fu3/Fu4 and specific primers 23SPecF/23SPecR of Pectobacterium spp.,a quintuple PCR reaction system for ginger soil-borne pathogens has been established(25.00μL):above primer dosage was 1.20,0.20,0.60,1.60,and 0.15μL respectively;2×PCR Mix 12.50μL;DNA templates of different pathogens were 1.00μL each;added ddH_(2)O to 25.00μL.Annealing temperature was optimized to 55.4℃.The specific fragments with sizes of 516,370,266,207,and 159 bp could be amplified simultaneously in the established quintuple PCR system,and the detection limit of this system for Ralstonia solanacearum,Enterobacter spp.and Pythium spp.reached 10^(-1)pg/μL,for Fusarium spp.and Pectobacterium spp.was 1 pg/μL,and for detecting five pathogens simultaneously was 10^(3)pg/μL.The multiplex PCR system established in this study could successfully detect the diseased plant samples from the field.【Conclusion】The quintuple PCR system established is able to rapid ly and accurately detect Ralstonia solanacearum,Fusarium spp.,Pectobacterium spp.,Enterobacter spp.,and Pythium spp.,which provides a useful tool for timely diagnosis and epidemic monitoring of various soil-borne diseases of ginger.展开更多
In this study,a multifunctional aptamer-conjugated magnetic covalent organic framework(COF)-CuO/Au nanozyme(MCOF-CuO/Au@apt)was developed as a“three-in-one”platform for dual-signal colorimetric and fluorescent detec...In this study,a multifunctional aptamer-conjugated magnetic covalent organic framework(COF)-CuO/Au nanozyme(MCOF-CuO/Au@apt)was developed as a“three-in-one”platform for dual-signal colorimetric and fluorescent detection of Vibrio parahaemolyticus.The nanozyme integrated magnetic separation,peroxidase-like catalytic activity,and specific target recognition through an aptamer-based strategy.Upon binding to V.parahaemolyticus,the catalytic oxidation of tetra-aminophenylethylene(TPE-4A)by the nanozyme was selectively inhibited,resulting in distinct colorimetric and fluorescent signals that significantly enhanced the detection accuracy and reliability.The proposed method exhibited high sensitivity,with limits of detection(LOD)of 21 and 7 CFU/mL for the colorimetric and fluorescent assays,respectively.The performance of this method was validated using real seafood samples,including Penaeus vannamei,Mytilus coruscus,and Crassostrea gigas,which showed high recovery rates(101.11%-107.30%)and excellent reproducibility.The system also demonstrated strong specificity and accuracy under various conditions,confirming its robustness and practical applicability.Collectively,this innovative platform presents a promising solution for the rapid,versatile,and sensitive detection of V.parahaemolyticus in seafood,with considerable potential to advance food safety diagnosis and on-site monitoring.展开更多
Diesel accounts for over 60%of the products derived from direct coal liquefaction(DCL).Compared to petroleum-based diesel,DCL diesel exhibits a cetane number ranging from 30 to 40,which fails to meet the automotive di...Diesel accounts for over 60%of the products derived from direct coal liquefaction(DCL).Compared to petroleum-based diesel,DCL diesel exhibits a cetane number ranging from 30 to 40,which fails to meet the automotive diesel standard requirement of≥45.Therefore,rapid and accurate analysis of its chemical composition is crucial for property optimization to meet fuel specifications by component blending.Thought traditional methods like gas chromatography offer high accuracy,they are unsuitable for rapid online analysis under industrial conditions.Near-infrared(NIR)spectroscopy can provide advantages in rapid,non-destructive analysis.Its application however,is limited by the complexity of spectral data interpretation.Machine learning(ML)is effective method for extracting valuable information from spectra and establishing high-precision prediction models.This study integrates NIR spectroscopy with ML to construct a spectral-composition database for DCL diesel.Feature extraction was performed using the correlation coefficient and mutual information methods to screen key wavelength variables and reduce data dimensionality.Subsequently,the predictive performance of three ML models—Lasso,SVR and XGBoost—was compared.Results indicate that excluding spectral data with absorbance greater than 1 significantly enhances model accuracy,increasing the test set R^(2) from 0.85 to 0.96.After feature extraction,the optimal number of wavelength variables was reduced to 177,substantially improving computational efficiency.Among the models evaluated,the SVR-MI-0.9 model,based on mutual information feature selection,demonstrated the best performance,achieving training and test set R^(2) values both exceeding 0.98.This model enables precise prediction of paraffin,naphthene,and aromatic hydrocarbon contents.This research provides a robust methodology for intelligent online quality monitoring.An intelligent NIR spectroscopy data analysis software was independently developed based on the established model.Compared with comprehensive two-dimensional gas chromatography,the software reduced the analysis time by over 98%,with an absolute prediction error below 0.2%.Thus,rapid analysis of DCL diesel components was successfully realized.展开更多
In the field of smart agriculture,accurate and efficient object detection technology is crucial for automated crop management.A particularly challenging task in this domain is small object detection,such as the identi...In the field of smart agriculture,accurate and efficient object detection technology is crucial for automated crop management.A particularly challenging task in this domain is small object detection,such as the identification of immature fruits or early stage disease spots.These objects pose significant difficulties due to their small pixel coverage,limited feature information,substantial scale variations,and high susceptibility to complex background interference.These challenges frequently result in inadequate accuracy and robustness in current detection models.This study addresses two critical needs in the cashew cultivation industry—fruitmaturity and anthracnose detection—by proposing an improved YOLOv11-NSDDil model.The method introduces three key technological innovations:(1)The SDDil module is designed and integrated into the backbone network.This module combines depthwise separable convolution with the SimAM attention mechanism to expand the receptive field and enhance contextual semantic capture at a low computational cost,effectively alleviating the feature deficiency problem caused by limited pixel coverage of small objects.Simultaneously,the SDmodule dynamically enhances discriminative features and suppresses background noise,significantly improving the model’s feature discrimination capability in complex environments;(2)The introduction of the DynamicScalSeq-Zoom_cat neck network,significantly improving multi-scale feature fusion;and(3)The optimization of the Minimum Point Distance Intersection over Union(MPDIoU)loss function,which enhances bounding box localization accuracy byminimizing vertex distance.Experimental results on a self-constructed cashew dataset containing 1123 images demonstrate significant performance improvements in the enhanced model:mAP50 reaches 0.825,a 4.6% increase compared to the originalYOLOv11;mAP50-95 improves to 0.624,a 6.5% increase;and recall rises to 0.777,a 2.4%increase.This provides a reliable technical solution for intelligent quality inspection of agricultural products and holds broad application prospects.展开更多
Dear Editor,This letter studies the motion planning issue for an autonomous underwater vehicle(AUV)in obstacle environment.We propose a novel integrated detection-communication waveform that enables simultaneous obsta...Dear Editor,This letter studies the motion planning issue for an autonomous underwater vehicle(AUV)in obstacle environment.We propose a novel integrated detection-communication waveform that enables simultaneous obstacle detection and self-localization.展开更多
Zero-day attacks present a critical cybersecurity challenge for Internet of things(IoT)infrastructures,where the inability of signature-based intrusion detection systems(IDSs)to recognize novel threat behaviors compro...Zero-day attacks present a critical cybersecurity challenge for Internet of things(IoT)infrastructures,where the inability of signature-based intrusion detection systems(IDSs)to recognize novel threat behaviors compromises both system reliability and operational continuity.Existing hybrid IDS solutions often struggle to balance accurate classification of known attacks with reliable anomaly detection,particularly under the computational constraints of IoT environments.To address this gap,we introduce ZeroDefense,an adaptive fusion-based IDS designed for simultaneous detection of known intrusions and emerging zero-day threats.The framework employs a four-layer architecture consisting of i)feature standardization and class balancing,ii)anomaly detection using isolation forest,autoencoder,and local outlier factor,iii)fine-grained attack classification via random forest,extreme gradient boosting(XGBoost),light gradient boosting machine(LightGBM),and attentive interpretable tabular learning(TabNet),and iv)a confidence-aware fusion engine that adaptively selects the most reliable decision path.Suspicious or previously unseen traffic is isolated early through fused anomaly scoring,while benign and known-malicious flows are processed through supervised classification for precise attack labeling.With an anomaly cascaded decision pipeline,a dynamic confidence-driven fusion mechanism,and a deploymentconscious design,ZeroDefense enables real-time inference on IoT edge gateways.Evaluation on the CICIoT2023 benchmark demonstrates 99.94% overall accuracy and 95.64%macro-average F1-score for known attacks,while 5.76% of traffic is successfully flagged as potential zero-day activity,with inference latency maintained below 100 ms/flow.These results indicate that ZeroDefense offers a scalable,resilient,and practically deployable defense capability for modern IoT infrastructures.展开更多
Distributed Denial-of-Service(DDoS)attacks pose severe threats to Industrial Control Networks(ICNs),where service disruption can cause significant economic losses and operational risks.Existing signature-based methods...Distributed Denial-of-Service(DDoS)attacks pose severe threats to Industrial Control Networks(ICNs),where service disruption can cause significant economic losses and operational risks.Existing signature-based methods are ineffective against novel attacks,and traditional machine learning models struggle to capture the complex temporal dependencies and dynamic traffic patterns inherent in ICN environments.To address these challenges,this study proposes a deep feature-driven hybrid framework that integrates Transformer,BiLSTM,and KNN to achieve accurate and robust DDoS detection.The Transformer component extracts global temporal dependencies from network traffic flows,while BiLSTM captures fine-grained sequential dynamics.The learned embeddings are then classified using an instance-based KNN layer,enhancing decision boundary precision.This cascaded architecture balances feature abstraction and locality preservation,improving both generalization and robustness.The proposed approach was evaluated on a newly collected real-time ICN traffic dataset and further validated using the public CIC-IDS2017 and Edge-IIoT datasets to demonstrate generalization.Comprehensive metrics including accuracy,precision,recall,F1-score,ROC-AUC,PR-AUC,false positive rate(FPR),and detection latency were employed.Results show that the hybrid framework achieves 98.42%accuracy with an ROC-AUC of 0.992 and FPR below 1%,outperforming baseline machine learning and deep learning models.Robustness experiments under Gaussian noise perturbations confirmed stable performance with less than 2%accuracy degradation.Moreover,detection latency remained below 2.1 ms per sample,indicating suitability for real-time ICS deployment.In summary,the proposed hybrid temporal learning and instance-based classification model offers a scalable and effective solution for DDoS detection in industrial control environments.By combining global contextual modeling,sequential learning,and instance-based refinement,the framework demonstrates strong adaptability across datasets and resilience against noise,providing practical utility for safeguarding critical infrastructure.展开更多
To address critical challenges in nighttime ship detection—high small-target missed detection(over 20%),insufficient lightweighting,and limited generalization due to scarce,low-quality datasets—this study proposes a...To address critical challenges in nighttime ship detection—high small-target missed detection(over 20%),insufficient lightweighting,and limited generalization due to scarce,low-quality datasets—this study proposes a systematic solution.First,a high-quality Night-Ships dataset is constructed via CycleGAN-based day-night transfer,combined with a dual-threshold cleaning strategy(Laplacian variance sharpness filtering and brightness-color deviation screening).Second,a Cross-stage Lightweight Fusion-You Only Look Once version 8(CLF-YOLOv8)is proposed with key improvements:the Neck network is reconstructed by replacing Cross Stage Partial(CSP)structure with the Cross Stage Partial Multi-Scale Convolutional Block(CSP-MSCB)and integrating Bidirectional Feature Pyramid Network(BiFPN)for weighted multi-scale fusion to enhance small-target detection;a Lightweight Shared Convolutional and Separated Batch Normalization Detection-Head(LSCSBD-Head)with shared convolutions and layer-wise Batch Normalization(BN)reduces parameters to 1.8M(42% fewer than YOLOv8n);and the FocalMinimum Point Distance Intersection over Union(Focal-MPDIoU)loss combines Minimum Point Distance Intersection over Union(MPDIoU)geometric constraints and Focal weighting to optimize low-overlap targets.Experiments show CLFYOLOv8 achieves 97.6%mAP@0.5(0.7% higher than YOLOv8n)with 1.8 M parameters,outperforming mainstream models in small-target detection,overlapping target discrimination,and adaptability to complex lighting.展开更多
Small object detection has been a focus of attention since the emergence of deep learning-based object detection.Although classical object detection frameworks have made significant contributions to the development of...Small object detection has been a focus of attention since the emergence of deep learning-based object detection.Although classical object detection frameworks have made significant contributions to the development of object detection,there are still many issues to be resolved in detecting small objects due to the inherent complexity and diversity of real-world visual scenes.In particular,the YOLO(You Only Look Once)series of detection models,renowned for their real-time performance,have undergone numerous adaptations aimed at improving the detection of small targets.In this survey,we summarize the state-of-the-art YOLO-based small object detection methods.This review presents a systematic categorization of YOLO-based approaches for small-object detection,organized into four methodological avenues,namely attention-based feature enhancement,detection-head optimization,loss function,and multi-scale feature fusion strategies.We then examine the principal challenges addressed by each category.Finally,we analyze the performance of thesemethods on public benchmarks and,by comparing current approaches,identify limitations and outline directions for future research.展开更多
The rapid proliferation of Internet of Things(IoT)devices in critical healthcare infrastructure has introduced significant security and privacy challenges that demand innovative,distributed architectural solutions.Thi...The rapid proliferation of Internet of Things(IoT)devices in critical healthcare infrastructure has introduced significant security and privacy challenges that demand innovative,distributed architectural solutions.This paper proposes FE-ACS(Fog-Edge Adaptive Cybersecurity System),a novel hierarchical security framework that intelligently distributes AI-powered anomaly detection algorithms across edge,fog,and cloud layers to optimize security efficacy,latency,and privacy.Our comprehensive evaluation demonstrates that FE-ACS achieves superior detection performance with an AUC-ROC of 0.985 and an F1-score of 0.923,while maintaining significantly lower end-to-end latency(18.7 ms)compared to cloud-centric(152.3 ms)and fog-only(34.5 ms)architectures.The system exhibits exceptional scalability,supporting up to 38,000 devices with logarithmic performance degradation—a 67×improvement over conventional cloud-based approaches.By incorporating differential privacy mechanisms with balanced privacy-utility tradeoffs(ε=1.0–1.5),FE-ACS maintains 90%–93%detection accuracy while ensuring strong privacy guarantees for sensitive healthcare data.Computational efficiency analysis reveals that our architecture achieves a detection rate of 12,400 events per second with only 12.3 mJ energy consumption per inference.In healthcare risk assessment,FE-ACS demonstrates robust operational viability with low patient safety risk(14.7%)and high system reliability(94.0%).The proposed framework represents a significant advancement in distributed security architectures,offering a scalable,privacy-preserving,and real-time solution for protecting healthcare IoT ecosystems against evolving cyber threats.展开更多
Breast cancer screening programs rely heavily on mammography for early detection;however,diagnostic performance is strongly affected by inter-reader variability,breast density,and the limitations of conven-tional comp...Breast cancer screening programs rely heavily on mammography for early detection;however,diagnostic performance is strongly affected by inter-reader variability,breast density,and the limitations of conven-tional computer-aided detection systems.Recent advances in deep learning have enabled more robust and scalable solutions for large-scale screening,yet a systematic comparison of modern object detection architectures on nationally representative datasets remains limited.This study presents a comprehensive quantitative comparison of prominent deep learning–based object detection architectures for Artificial Intelligence-assisted mammography analysis using the MammosighTR dataset,developed within the Turkish National Breast Cancer Screening Program.The dataset comprises 12,740 patient cases collected between 2016 and 2022,annotated with BI-RADS categories,breast density levels,and lesion localization labels.A total of 31 models were evaluated,including One-Stage,Two-Stage,and Transformer-based architectures,under a unified experimental framework at both patient and breast levels.The results demonstrate that Two-Stage architectures consistently outperform One-Stage models,achieving approximately 2%–4%higher Macro F1-Scores and more balanced precision–recall trade-offs,with Double-Head R-CNN and Dynamic R-CNN yielding the highest overall performance(Macro F1≈0.84–0.86).This advantage is primarily attributed to the region proposal mechanism and improved class balance inherent to Two-Stage designs.One-Stage detectors exhibited higher sensitivity and faster inference,reaching Recall values above 0.88,but experienced minor reductions in Precision and overall accuracy(≈1%–2%)compared with Two-Stage models.Among Transformer-based architectures,Deformable DEtection TRansformer demonstrated strong robustness and consistency across datasets,achieving Macro F1-Scores comparable to CNN-based detectors(≈0.83–0.85)while exhibiting minimal performance degradation under distributional shifts.Breast density–based analysis revealed increased misclassification rates in medium-density categories(types B and C),whereas Transformer-based architectures maintained more stable performance in high-density type D tissue.These findings quantitatively confirm that both architectural design and tissue characteristics play a decisive role in diagnostic accuracy.Overall,the study provides a reproducible benchmark and highlights the potential of hybrid approaches that combine the accuracy of Two-Stage detectors with the contextual modeling capability of Transformer architectures for clinically reliable breast cancer screening systems.展开更多
Log anomaly detection is essential for maintaining the reliability and security of large-scale networked systems.Most traditional techniques rely on log parsing in the reprocessing stage and utilize handcrafted featur...Log anomaly detection is essential for maintaining the reliability and security of large-scale networked systems.Most traditional techniques rely on log parsing in the reprocessing stage and utilize handcrafted features that limit their adaptability across various systems.In this study,we propose a hybrid model,BertGCN,that integrates BERT-based contextual embedding with Graph Convolutional Networks(GCNs)to identify anomalies in raw system logs,thereby eliminating the need for log parsing.TheBERT module captures semantic representations of log messages,while the GCN models the structural relationships among log entries through a text-based graph.This combination enables BertGCN to capture both the contextual and semantic characteristics of log data.BertGCN showed excellent performance on the HDFS and BGL datasets,demonstrating its effectiveness and resilience in detecting anomalies.Compared to multiple baselines,our proposed BertGCN showed improved precision,recall,and F1 scores.展开更多
Adversarial Reinforcement Learning(ARL)models for intelligent devices and Network Intrusion Detection Systems(NIDS)improve systemresilience against sophisticated cyber-attacks.As a core component of ARL,Adversarial Tr...Adversarial Reinforcement Learning(ARL)models for intelligent devices and Network Intrusion Detection Systems(NIDS)improve systemresilience against sophisticated cyber-attacks.As a core component of ARL,Adversarial Training(AT)enables NIDS agents to discover and prevent newattack paths by exposing them to competing examples,thereby increasing detection accuracy,reducing False Positives(FPs),and enhancing network security.To develop robust decision-making capabilities for real-world network disruptions and hostile activity,NIDS agents are trained in adversarial scenarios to monitor the current state and notify management of any abnormal or malicious activity.The accuracy and timeliness of the IDS were crucial to the network’s availability and reliability at this time.This paper analyzes ARL applications in NIDS,revealing State-of-The-Art(SoTA)methodology,issues,and future research prospects.This includes Reinforcement Machine Learning(RML)-based NIDS,which enables an agent to interact with the environment to achieve a goal,andDeep Reinforcement Learning(DRL)-based NIDS,which can solve complex decision-making problems.Additionally,this survey study addresses cybersecurity adversarial circumstances and their importance for ARL and NIDS.Architectural design,RL algorithms,feature representation,and training methodologies are examined in the ARL-NIDS study.This comprehensive study evaluates ARL for intelligent NIDS research,benefiting cybersecurity researchers,practitioners,and policymakers.The report promotes cybersecurity defense research and innovation.展开更多
With the increasing emphasis on personal information protection,encryption through security protocols has emerged as a critical requirement in data transmission and reception processes.Nevertheless,IoT ecosystems comp...With the increasing emphasis on personal information protection,encryption through security protocols has emerged as a critical requirement in data transmission and reception processes.Nevertheless,IoT ecosystems comprise heterogeneous networks where outdated systems coexist with the latest devices,spanning a range of devices from non-encrypted ones to fully encrypted ones.Given the limited visibility into payloads in this context,this study investigates AI-based attack detection methods that leverage encrypted traffic metadata,eliminating the need for decryption and minimizing system performance degradation—especially in light of these heterogeneous devices.Using the UNSW-NB15 and CICIoT-2023 dataset,encrypted and unencrypted traffic were categorized according to security protocol,and AI-based intrusion detection experiments were conducted for each traffic type based on metadata.To mitigate the problem of class imbalance,eight different data sampling techniques were applied.The effectiveness of these sampling techniques was then comparatively analyzed using two ensemble models and three Deep Learning(DL)models from various perspectives.The experimental results confirmed that metadata-based attack detection is feasible using only encrypted traffic.In the UNSW-NB15 dataset,the f1-score of encrypted traffic was approximately 0.98,which is 4.3%higher than that of unencrypted traffic(approximately 0.94).In addition,analysis of the encrypted traffic in the CICIoT-2023 dataset using the same method showed a significantly lower f1-score of roughly 0.43,indicating that the quality of the dataset and the preprocessing approach have a substantial impact on detection performance.Furthermore,when data sampling techniques were applied to encrypted traffic,the recall in the UNSWNB15(Encrypted)dataset improved by up to 23.0%,and in the CICIoT-2023(Encrypted)dataset by 20.26%,showing a similar level of improvement.Notably,in CICIoT-2023,f1-score and Receiver Operation Characteristic-Area Under the Curve(ROC-AUC)increased by 59.0%and 55.94%,respectively.These results suggest that data sampling can have a positive effect even in encrypted environments.However,the extent of the improvement may vary depending on data quality,model architecture,and sampling strategy.展开更多
基金supported by the National Natural Science Foundation of China(grant no.61805147 and 52103316).
文摘Aqueous lead monosulfide(PbS)quantum dots(QDs)fabricated by conventional approaches display poor photodetection performance and unsatisfactory chemical stability,so various strategies for well-defined PbS QD-based heterostructures have been developed,which are usually complicated and unsuitable for largescale production.In this work,homogeneous ultrasmall,uniform ternary Pb_(1−x)Cd_(x)S QDs are rationally designed and successfully fabricated by an in situ aqueous coprecipitation method.
基金National Natural Science Foundation of China,Grant/Award Numbers:62074102,62104156,21961160720Open Research Fund of Songshan Lake Materials Laboratory,Grant/Award Number:2021SLABFK02+1 种基金Guangdong Basic and Applied Basic Research Foundation,Grant/Award Numbers:2022A1515010979,2023A1515011256Science and Technology Plan Project of Shenzhen,Grant/Award。
文摘Kesterite Cu_(2)ZnSn(S,Se)_(4)(CZTSSe)is a promising candidate for photodetector(PD)applications thanks to its excellent optoelectronic properties.In this work,a green solution-processed spin coating and selenization-processed thermodynamic or kinetic growth of high-quality narrow bandgap kesterite CZTSSe thin film is developed.A self-powered CZTSSe/CdS thin-film PD is then successfully fabricated.Under optimization of light absorber and heterojunction interface,especially tailoring the defect and carrier kinetics,it can achieve broadband response from300 to 1300 nm,accompaniedwith a high responsivity of 1.37A/W,specific detectivity(D*)up to 4.0×10^(14)Jones under 5 nW/cm^(2),a linear dynamic range(LDR)of 126 dB,and a maximum Ilight/Idark ratio of 1.3×10^(8)within the LDR,and ultrafast response speed(rise/decay time of 16 ns/85 ns),representing the leading-level performance to date,which is superior to those of commercial andwell-researched photodiodes.Additionally,an imaging system with a 905nm laser is built for weak light response evaluation,and can respond to 718 pW weak light and infrared imaging at a wavelength as low as 5 nW/cm2.It has also been employed for photoplethysmography detection of pulsating signals at both the finger and wrist,presenting obvious arterial blood volume changes,demonstrating great application potential in broadband and weak light photodetection scenarios.
基金supported by the National Natural Science Foundation of China(No.62276204)the Fundamental Research Funds for the Central Universities,China(No.YJSJ24011)+1 种基金the Natural Science Basic Research Program of Shaanxi,China(Nos.2022JM-340 and 2023-JC-QN-0710)the China Postdoctoral Science Foundation(Nos.2020T130494 and 2018M633470)。
文摘Visible and infrared(RGB-IR)fusion object detection plays an important role in security,disaster relief,etc.In recent years,deep-learning-based RGB-IR fusion detection methods have been developing rapidly,but still struggle to deal with the complex and changing scenarios captured by drones,mainly due to two reasons:(A)RGB-IR fusion detectors are susceptible to inferior inputs that degrade performance and stability.(B)RGB-IR fusion detectors are susceptible to redundant features that reduce accuracy and efficiency.In this paper,an innovative RGB-IR fusion detection framework based on global-local feature optimization,named GLFDet,is proposed to improve the detection performance and efficiency of drone-captured objects.The key components of GLFDet include a Global Feature Optimization(GFO)module,a Local Feature Optimization(LFO)module and a Channel Separation Fusion(CSF)module.Specifically,GFO calculates the information content of the input image from the frequency domain and optimizes the features holistically.Then,LFO dynamically selects high-value features and filters out low-value features before fusion,which significantly improves the efficiency of fusion.Finally,CSF fuses the RGB and IR features across the corresponding channels,which avoids the rearrangement of the channel relationships and enhances the model stability.Extensive experimental results show that the proposed method achieves the best performance on three popular RGB-IR datasets Drone Vehicle,VEDAI,and LLVIP.In addition,GLFDet is more lightweight than other comparable models,making it more appealing to edge devices such as drones.The code is available at https://github.com/lao chen330/GLFDet.
文摘Underwater pipeline inspection plays a vital role in the proactive maintenance and management of critical marine infrastructure and subaquatic systems.However,the inspection of underwater pipelines presents a challenge due to factors such as light scattering,absorption,restricted visibility,and ambient noise.The advancement of deep learning has introduced powerful techniques for processing large amounts of unstructured and imperfect data collected from underwater environments.This study evaluated the efficacy of the You Only Look Once(YOLO)algorithm,a real-time object detection and localization model based on convolutional neural networks,in identifying and classifying various types of pipeline defects in underwater settings.YOLOv8,the latest evolution in the YOLO family,integrates advanced capabilities,such as anchor-free detection,a cross-stage partial network backbone for efficient feature extraction,and a feature pyramid network+path aggregation network neck for robust multi-scale object detection,which make it particularly well-suited for complex underwater environments.Due to the lack of suitable open-access datasets for underwater pipeline defects,a custom dataset was captured using a remotely operated vehicle in a controlled environment.This application has the following assets available for use.Extensive experimentation demonstrated that YOLOv8 X-Large consistently outperformed other models in terms of pipe defect detection and classification and achieved a strong balance between precision and recall in identifying pipeline cracks,rust,corners,defective welds,flanges,tapes,and holes.This research establishes the baseline performance of YOLOv8 for underwater defect detection and showcases its potential to enhance the reliability and efficiency of pipeline inspection tasks in challenging underwater environments.
基金National Natural Science Foundation of China(32270237)Guangxi Key Research and Development Plan Project(Guike AB21238002)Basic Scientific Research Project of Guangxi Academy of Agricultural Sciences(Guinongke 2024YP082)。
文摘【Objective】This study aimed to establish a quintuple PCR method for rapid and simultaneous detection of Ralstonia solanacearum,Fusarium spp.,Pectobacterium spp.,Enterobacter spp.,and Pythium spp.,which provided technical support for early diagnosis of various soil-borne diseases on ginger.【Method】For five types of soil-borne pathogens causing ginger bacterial wilt and rhizome rot,specific primer combinations were designed and screened,the optimal quintuple reaction system was established by exploring optimal primer concentrations,annealing temperature,and sensitivity,and was applied to detect field plant samples to verify its utility.【Result】Specific primers pairs Rs1F/Rs1R,En1F/En1R,and Py1F/Py1R were designed according to flic gene of Ralstonia solanacearum,rpoB gene of Enterobacter spp.,and 18S rDNA of Pythium spp.,and combined with reported Fusarium spp.specific primers Fu3/Fu4 and specific primers 23SPecF/23SPecR of Pectobacterium spp.,a quintuple PCR reaction system for ginger soil-borne pathogens has been established(25.00μL):above primer dosage was 1.20,0.20,0.60,1.60,and 0.15μL respectively;2×PCR Mix 12.50μL;DNA templates of different pathogens were 1.00μL each;added ddH_(2)O to 25.00μL.Annealing temperature was optimized to 55.4℃.The specific fragments with sizes of 516,370,266,207,and 159 bp could be amplified simultaneously in the established quintuple PCR system,and the detection limit of this system for Ralstonia solanacearum,Enterobacter spp.and Pythium spp.reached 10^(-1)pg/μL,for Fusarium spp.and Pectobacterium spp.was 1 pg/μL,and for detecting five pathogens simultaneously was 10^(3)pg/μL.The multiplex PCR system established in this study could successfully detect the diseased plant samples from the field.【Conclusion】The quintuple PCR system established is able to rapid ly and accurately detect Ralstonia solanacearum,Fusarium spp.,Pectobacterium spp.,Enterobacter spp.,and Pythium spp.,which provides a useful tool for timely diagnosis and epidemic monitoring of various soil-borne diseases of ginger.
文摘In this study,a multifunctional aptamer-conjugated magnetic covalent organic framework(COF)-CuO/Au nanozyme(MCOF-CuO/Au@apt)was developed as a“three-in-one”platform for dual-signal colorimetric and fluorescent detection of Vibrio parahaemolyticus.The nanozyme integrated magnetic separation,peroxidase-like catalytic activity,and specific target recognition through an aptamer-based strategy.Upon binding to V.parahaemolyticus,the catalytic oxidation of tetra-aminophenylethylene(TPE-4A)by the nanozyme was selectively inhibited,resulting in distinct colorimetric and fluorescent signals that significantly enhanced the detection accuracy and reliability.The proposed method exhibited high sensitivity,with limits of detection(LOD)of 21 and 7 CFU/mL for the colorimetric and fluorescent assays,respectively.The performance of this method was validated using real seafood samples,including Penaeus vannamei,Mytilus coruscus,and Crassostrea gigas,which showed high recovery rates(101.11%-107.30%)and excellent reproducibility.The system also demonstrated strong specificity and accuracy under various conditions,confirming its robustness and practical applicability.Collectively,this innovative platform presents a promising solution for the rapid,versatile,and sensitive detection of V.parahaemolyticus in seafood,with considerable potential to advance food safety diagnosis and on-site monitoring.
基金Supported by National Natural Science Foundation of China(U24B6018,22178243)。
文摘Diesel accounts for over 60%of the products derived from direct coal liquefaction(DCL).Compared to petroleum-based diesel,DCL diesel exhibits a cetane number ranging from 30 to 40,which fails to meet the automotive diesel standard requirement of≥45.Therefore,rapid and accurate analysis of its chemical composition is crucial for property optimization to meet fuel specifications by component blending.Thought traditional methods like gas chromatography offer high accuracy,they are unsuitable for rapid online analysis under industrial conditions.Near-infrared(NIR)spectroscopy can provide advantages in rapid,non-destructive analysis.Its application however,is limited by the complexity of spectral data interpretation.Machine learning(ML)is effective method for extracting valuable information from spectra and establishing high-precision prediction models.This study integrates NIR spectroscopy with ML to construct a spectral-composition database for DCL diesel.Feature extraction was performed using the correlation coefficient and mutual information methods to screen key wavelength variables and reduce data dimensionality.Subsequently,the predictive performance of three ML models—Lasso,SVR and XGBoost—was compared.Results indicate that excluding spectral data with absorbance greater than 1 significantly enhances model accuracy,increasing the test set R^(2) from 0.85 to 0.96.After feature extraction,the optimal number of wavelength variables was reduced to 177,substantially improving computational efficiency.Among the models evaluated,the SVR-MI-0.9 model,based on mutual information feature selection,demonstrated the best performance,achieving training and test set R^(2) values both exceeding 0.98.This model enables precise prediction of paraffin,naphthene,and aromatic hydrocarbon contents.This research provides a robust methodology for intelligent online quality monitoring.An intelligent NIR spectroscopy data analysis software was independently developed based on the established model.Compared with comprehensive two-dimensional gas chromatography,the software reduced the analysis time by over 98%,with an absolute prediction error below 0.2%.Thus,rapid analysis of DCL diesel components was successfully realized.
基金supported by Hebei North University Doctoral Research Fund Project(No.BSJJ202315)the Youth Research Fund Project of Higher Education Institutions in Hebei Province(No.QN2024146).
文摘In the field of smart agriculture,accurate and efficient object detection technology is crucial for automated crop management.A particularly challenging task in this domain is small object detection,such as the identification of immature fruits or early stage disease spots.These objects pose significant difficulties due to their small pixel coverage,limited feature information,substantial scale variations,and high susceptibility to complex background interference.These challenges frequently result in inadequate accuracy and robustness in current detection models.This study addresses two critical needs in the cashew cultivation industry—fruitmaturity and anthracnose detection—by proposing an improved YOLOv11-NSDDil model.The method introduces three key technological innovations:(1)The SDDil module is designed and integrated into the backbone network.This module combines depthwise separable convolution with the SimAM attention mechanism to expand the receptive field and enhance contextual semantic capture at a low computational cost,effectively alleviating the feature deficiency problem caused by limited pixel coverage of small objects.Simultaneously,the SDmodule dynamically enhances discriminative features and suppresses background noise,significantly improving the model’s feature discrimination capability in complex environments;(2)The introduction of the DynamicScalSeq-Zoom_cat neck network,significantly improving multi-scale feature fusion;and(3)The optimization of the Minimum Point Distance Intersection over Union(MPDIoU)loss function,which enhances bounding box localization accuracy byminimizing vertex distance.Experimental results on a self-constructed cashew dataset containing 1123 images demonstrate significant performance improvements in the enhanced model:mAP50 reaches 0.825,a 4.6% increase compared to the originalYOLOv11;mAP50-95 improves to 0.624,a 6.5% increase;and recall rises to 0.777,a 2.4%increase.This provides a reliable technical solution for intelligent quality inspection of agricultural products and holds broad application prospects.
基金supported in part by the National Natural Science Foundation of China(U25A20473,62222314)the YanZhao Young Scientist Project of Hebei Province(F2024203047)+2 种基金the Natural Science Foundation of Hebei Province(F2022203001,F2024203072)the State Key Laboratory of Submarine Geoscience(sglkt2025-7)the Education Department Foundation of Hebei Province(JCZX2025027)。
文摘Dear Editor,This letter studies the motion planning issue for an autonomous underwater vehicle(AUV)in obstacle environment.We propose a novel integrated detection-communication waveform that enables simultaneous obstacle detection and self-localization.
文摘Zero-day attacks present a critical cybersecurity challenge for Internet of things(IoT)infrastructures,where the inability of signature-based intrusion detection systems(IDSs)to recognize novel threat behaviors compromises both system reliability and operational continuity.Existing hybrid IDS solutions often struggle to balance accurate classification of known attacks with reliable anomaly detection,particularly under the computational constraints of IoT environments.To address this gap,we introduce ZeroDefense,an adaptive fusion-based IDS designed for simultaneous detection of known intrusions and emerging zero-day threats.The framework employs a four-layer architecture consisting of i)feature standardization and class balancing,ii)anomaly detection using isolation forest,autoencoder,and local outlier factor,iii)fine-grained attack classification via random forest,extreme gradient boosting(XGBoost),light gradient boosting machine(LightGBM),and attentive interpretable tabular learning(TabNet),and iv)a confidence-aware fusion engine that adaptively selects the most reliable decision path.Suspicious or previously unseen traffic is isolated early through fused anomaly scoring,while benign and known-malicious flows are processed through supervised classification for precise attack labeling.With an anomaly cascaded decision pipeline,a dynamic confidence-driven fusion mechanism,and a deploymentconscious design,ZeroDefense enables real-time inference on IoT edge gateways.Evaluation on the CICIoT2023 benchmark demonstrates 99.94% overall accuracy and 95.64%macro-average F1-score for known attacks,while 5.76% of traffic is successfully flagged as potential zero-day activity,with inference latency maintained below 100 ms/flow.These results indicate that ZeroDefense offers a scalable,resilient,and practically deployable defense capability for modern IoT infrastructures.
基金supported by the Extral High Voltage Power Transmission Company,China Southern Power Grid Co.,Ltd.
文摘Distributed Denial-of-Service(DDoS)attacks pose severe threats to Industrial Control Networks(ICNs),where service disruption can cause significant economic losses and operational risks.Existing signature-based methods are ineffective against novel attacks,and traditional machine learning models struggle to capture the complex temporal dependencies and dynamic traffic patterns inherent in ICN environments.To address these challenges,this study proposes a deep feature-driven hybrid framework that integrates Transformer,BiLSTM,and KNN to achieve accurate and robust DDoS detection.The Transformer component extracts global temporal dependencies from network traffic flows,while BiLSTM captures fine-grained sequential dynamics.The learned embeddings are then classified using an instance-based KNN layer,enhancing decision boundary precision.This cascaded architecture balances feature abstraction and locality preservation,improving both generalization and robustness.The proposed approach was evaluated on a newly collected real-time ICN traffic dataset and further validated using the public CIC-IDS2017 and Edge-IIoT datasets to demonstrate generalization.Comprehensive metrics including accuracy,precision,recall,F1-score,ROC-AUC,PR-AUC,false positive rate(FPR),and detection latency were employed.Results show that the hybrid framework achieves 98.42%accuracy with an ROC-AUC of 0.992 and FPR below 1%,outperforming baseline machine learning and deep learning models.Robustness experiments under Gaussian noise perturbations confirmed stable performance with less than 2%accuracy degradation.Moreover,detection latency remained below 2.1 ms per sample,indicating suitability for real-time ICS deployment.In summary,the proposed hybrid temporal learning and instance-based classification model offers a scalable and effective solution for DDoS detection in industrial control environments.By combining global contextual modeling,sequential learning,and instance-based refinement,the framework demonstrates strong adaptability across datasets and resilience against noise,providing practical utility for safeguarding critical infrastructure.
基金the Shandong Provincial Key Research and Development Program(Grant No.2024SFGC0201).
文摘To address critical challenges in nighttime ship detection—high small-target missed detection(over 20%),insufficient lightweighting,and limited generalization due to scarce,low-quality datasets—this study proposes a systematic solution.First,a high-quality Night-Ships dataset is constructed via CycleGAN-based day-night transfer,combined with a dual-threshold cleaning strategy(Laplacian variance sharpness filtering and brightness-color deviation screening).Second,a Cross-stage Lightweight Fusion-You Only Look Once version 8(CLF-YOLOv8)is proposed with key improvements:the Neck network is reconstructed by replacing Cross Stage Partial(CSP)structure with the Cross Stage Partial Multi-Scale Convolutional Block(CSP-MSCB)and integrating Bidirectional Feature Pyramid Network(BiFPN)for weighted multi-scale fusion to enhance small-target detection;a Lightweight Shared Convolutional and Separated Batch Normalization Detection-Head(LSCSBD-Head)with shared convolutions and layer-wise Batch Normalization(BN)reduces parameters to 1.8M(42% fewer than YOLOv8n);and the FocalMinimum Point Distance Intersection over Union(Focal-MPDIoU)loss combines Minimum Point Distance Intersection over Union(MPDIoU)geometric constraints and Focal weighting to optimize low-overlap targets.Experiments show CLFYOLOv8 achieves 97.6%mAP@0.5(0.7% higher than YOLOv8n)with 1.8 M parameters,outperforming mainstream models in small-target detection,overlapping target discrimination,and adaptability to complex lighting.
基金supported in part by the by Chongqing Research Program of Basic Research and Frontier Technology under Grant CSTB2025NSCQ-GPX1309.
文摘Small object detection has been a focus of attention since the emergence of deep learning-based object detection.Although classical object detection frameworks have made significant contributions to the development of object detection,there are still many issues to be resolved in detecting small objects due to the inherent complexity and diversity of real-world visual scenes.In particular,the YOLO(You Only Look Once)series of detection models,renowned for their real-time performance,have undergone numerous adaptations aimed at improving the detection of small targets.In this survey,we summarize the state-of-the-art YOLO-based small object detection methods.This review presents a systematic categorization of YOLO-based approaches for small-object detection,organized into four methodological avenues,namely attention-based feature enhancement,detection-head optimization,loss function,and multi-scale feature fusion strategies.We then examine the principal challenges addressed by each category.Finally,we analyze the performance of thesemethods on public benchmarks and,by comparing current approaches,identify limitations and outline directions for future research.
基金supported by the Deanship of Graduate Studies and Scientific Research at Jouf University under grant No.(DGSSR-2025-02-01276).
文摘The rapid proliferation of Internet of Things(IoT)devices in critical healthcare infrastructure has introduced significant security and privacy challenges that demand innovative,distributed architectural solutions.This paper proposes FE-ACS(Fog-Edge Adaptive Cybersecurity System),a novel hierarchical security framework that intelligently distributes AI-powered anomaly detection algorithms across edge,fog,and cloud layers to optimize security efficacy,latency,and privacy.Our comprehensive evaluation demonstrates that FE-ACS achieves superior detection performance with an AUC-ROC of 0.985 and an F1-score of 0.923,while maintaining significantly lower end-to-end latency(18.7 ms)compared to cloud-centric(152.3 ms)and fog-only(34.5 ms)architectures.The system exhibits exceptional scalability,supporting up to 38,000 devices with logarithmic performance degradation—a 67×improvement over conventional cloud-based approaches.By incorporating differential privacy mechanisms with balanced privacy-utility tradeoffs(ε=1.0–1.5),FE-ACS maintains 90%–93%detection accuracy while ensuring strong privacy guarantees for sensitive healthcare data.Computational efficiency analysis reveals that our architecture achieves a detection rate of 12,400 events per second with only 12.3 mJ energy consumption per inference.In healthcare risk assessment,FE-ACS demonstrates robust operational viability with low patient safety risk(14.7%)and high system reliability(94.0%).The proposed framework represents a significant advancement in distributed security architectures,offering a scalable,privacy-preserving,and real-time solution for protecting healthcare IoT ecosystems against evolving cyber threats.
文摘Breast cancer screening programs rely heavily on mammography for early detection;however,diagnostic performance is strongly affected by inter-reader variability,breast density,and the limitations of conven-tional computer-aided detection systems.Recent advances in deep learning have enabled more robust and scalable solutions for large-scale screening,yet a systematic comparison of modern object detection architectures on nationally representative datasets remains limited.This study presents a comprehensive quantitative comparison of prominent deep learning–based object detection architectures for Artificial Intelligence-assisted mammography analysis using the MammosighTR dataset,developed within the Turkish National Breast Cancer Screening Program.The dataset comprises 12,740 patient cases collected between 2016 and 2022,annotated with BI-RADS categories,breast density levels,and lesion localization labels.A total of 31 models were evaluated,including One-Stage,Two-Stage,and Transformer-based architectures,under a unified experimental framework at both patient and breast levels.The results demonstrate that Two-Stage architectures consistently outperform One-Stage models,achieving approximately 2%–4%higher Macro F1-Scores and more balanced precision–recall trade-offs,with Double-Head R-CNN and Dynamic R-CNN yielding the highest overall performance(Macro F1≈0.84–0.86).This advantage is primarily attributed to the region proposal mechanism and improved class balance inherent to Two-Stage designs.One-Stage detectors exhibited higher sensitivity and faster inference,reaching Recall values above 0.88,but experienced minor reductions in Precision and overall accuracy(≈1%–2%)compared with Two-Stage models.Among Transformer-based architectures,Deformable DEtection TRansformer demonstrated strong robustness and consistency across datasets,achieving Macro F1-Scores comparable to CNN-based detectors(≈0.83–0.85)while exhibiting minimal performance degradation under distributional shifts.Breast density–based analysis revealed increased misclassification rates in medium-density categories(types B and C),whereas Transformer-based architectures maintained more stable performance in high-density type D tissue.These findings quantitatively confirm that both architectural design and tissue characteristics play a decisive role in diagnostic accuracy.Overall,the study provides a reproducible benchmark and highlights the potential of hybrid approaches that combine the accuracy of Two-Stage detectors with the contextual modeling capability of Transformer architectures for clinically reliable breast cancer screening systems.
基金funded by the Deanship of Scientific Research(DSR)at King Abdulaziz University,Jeddah,under grant no.(GPIP:1074-612-2024).
文摘Log anomaly detection is essential for maintaining the reliability and security of large-scale networked systems.Most traditional techniques rely on log parsing in the reprocessing stage and utilize handcrafted features that limit their adaptability across various systems.In this study,we propose a hybrid model,BertGCN,that integrates BERT-based contextual embedding with Graph Convolutional Networks(GCNs)to identify anomalies in raw system logs,thereby eliminating the need for log parsing.TheBERT module captures semantic representations of log messages,while the GCN models the structural relationships among log entries through a text-based graph.This combination enables BertGCN to capture both the contextual and semantic characteristics of log data.BertGCN showed excellent performance on the HDFS and BGL datasets,demonstrating its effectiveness and resilience in detecting anomalies.Compared to multiple baselines,our proposed BertGCN showed improved precision,recall,and F1 scores.
文摘Adversarial Reinforcement Learning(ARL)models for intelligent devices and Network Intrusion Detection Systems(NIDS)improve systemresilience against sophisticated cyber-attacks.As a core component of ARL,Adversarial Training(AT)enables NIDS agents to discover and prevent newattack paths by exposing them to competing examples,thereby increasing detection accuracy,reducing False Positives(FPs),and enhancing network security.To develop robust decision-making capabilities for real-world network disruptions and hostile activity,NIDS agents are trained in adversarial scenarios to monitor the current state and notify management of any abnormal or malicious activity.The accuracy and timeliness of the IDS were crucial to the network’s availability and reliability at this time.This paper analyzes ARL applications in NIDS,revealing State-of-The-Art(SoTA)methodology,issues,and future research prospects.This includes Reinforcement Machine Learning(RML)-based NIDS,which enables an agent to interact with the environment to achieve a goal,andDeep Reinforcement Learning(DRL)-based NIDS,which can solve complex decision-making problems.Additionally,this survey study addresses cybersecurity adversarial circumstances and their importance for ARL and NIDS.Architectural design,RL algorithms,feature representation,and training methodologies are examined in the ARL-NIDS study.This comprehensive study evaluates ARL for intelligent NIDS research,benefiting cybersecurity researchers,practitioners,and policymakers.The report promotes cybersecurity defense research and innovation.
基金supported by the Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)(No.RS-2023-00235509Development of security monitoring technology based network behavior against encrypted cyber threats in ICT convergence environment).
文摘With the increasing emphasis on personal information protection,encryption through security protocols has emerged as a critical requirement in data transmission and reception processes.Nevertheless,IoT ecosystems comprise heterogeneous networks where outdated systems coexist with the latest devices,spanning a range of devices from non-encrypted ones to fully encrypted ones.Given the limited visibility into payloads in this context,this study investigates AI-based attack detection methods that leverage encrypted traffic metadata,eliminating the need for decryption and minimizing system performance degradation—especially in light of these heterogeneous devices.Using the UNSW-NB15 and CICIoT-2023 dataset,encrypted and unencrypted traffic were categorized according to security protocol,and AI-based intrusion detection experiments were conducted for each traffic type based on metadata.To mitigate the problem of class imbalance,eight different data sampling techniques were applied.The effectiveness of these sampling techniques was then comparatively analyzed using two ensemble models and three Deep Learning(DL)models from various perspectives.The experimental results confirmed that metadata-based attack detection is feasible using only encrypted traffic.In the UNSW-NB15 dataset,the f1-score of encrypted traffic was approximately 0.98,which is 4.3%higher than that of unencrypted traffic(approximately 0.94).In addition,analysis of the encrypted traffic in the CICIoT-2023 dataset using the same method showed a significantly lower f1-score of roughly 0.43,indicating that the quality of the dataset and the preprocessing approach have a substantial impact on detection performance.Furthermore,when data sampling techniques were applied to encrypted traffic,the recall in the UNSWNB15(Encrypted)dataset improved by up to 23.0%,and in the CICIoT-2023(Encrypted)dataset by 20.26%,showing a similar level of improvement.Notably,in CICIoT-2023,f1-score and Receiver Operation Characteristic-Area Under the Curve(ROC-AUC)increased by 59.0%and 55.94%,respectively.These results suggest that data sampling can have a positive effect even in encrypted environments.However,the extent of the improvement may vary depending on data quality,model architecture,and sampling strategy.
