Search Results (260)

The rapid growth of web-based services has intensified the need for reliable mechanisms to distinguish malicious Uniform Resource Locators (URLs) from legitimate ones. Phishing campaigns, malware distribution networks, and defacement operations increasingly rely on deceptive web addresses to compromise unsuspecting users and critical infrastructure. Accurate URL classification plays a critical role in mitigating phishing attacks, malware distribution, and other cyber threats. This study presents a machine learning framework for detecting malicious URLs in cybersecurity applications. This study presents a comprehensive empirical evaluation of multiple machine learning and deep learning approaches for URL classification under two experimental settings: training with the complete feature set and training with a reduced subset obtained through Particle Swarm Optimization (PSO). The framework incorporates advanced feature engineering techniques that capture domain-specific characteristics of malicious URLs. Seventeen classifiers, encompassing traditional ensemble methods, neural architectures, and hybrid stacking configurations, were evaluated on a publicly available dataset of 651,191 URL samples retrieved from Kaggle. The PSO reduced the original ten-feature space to seven discriminative features, representing a 30% dimensionality reduction. Experimental results demonstrate that all-feature models consistently outperformed their PSO-reduced counterparts, with Random Forest achieving the highest classification accuracy of 91.90% and an F1-score of 0.9165. The findings offer empirical grounding for the design of computationally efficient URL threat detection systems and provide actionable directions for future research in adversarial machine learning and real-time cybersecurity pipelines. Full article

Improving the decoding accuracy and information transfer rate (ITR) of steady-state visual evoked potential brain–computer interface (SSVEP-BCI) systems, while enhancing cross-subject generalization and reducing calibration cost, is essential for practical deployment. This study proposes an end-to-end framework that integrates adaptive filtering with semi-supervised domain adaptation. The framework incorporates a Gabor adaptive filter bank (G-AFB) to optimize time–frequency representations and extract features matched to individual neural responses. It also introduces a three-stage semi-supervised domain-adversarial neural network (TriS-DANN), which combines unsupervised pre-alignment and supervised fine-tuning to align cross-subject feature distributions and enable lightweight calibration. On the 1.0 s public benchmark dataset, G-AFB-tCNN achieved 89.13% accuracy, a 4.63 percentage-point improvement over its conventional filter-bank counterpart. On the 0.4 s in-house dataset, G-AFB-tCNN achieved 91.85% accuracy, a 3.22 percentage-point improvement over the conventional fixed filter bank. In transfer learning, TriS-DANN reached 86.60% accuracy using 0.4 s segments extracted from the stimulation period and only 23.07% of the available target-domain training/calibration trials, demonstrating higher efficiency and stability than conventional fine-tuning. These results support the proposed framework as a feasible route toward reliable, low-calibration SSVEP-BCI systems. Full article

Mangrove ecosystems are recognized for their exceptional carbon sequestration potential and crucial contribution to coastal ecological balance. However, the sharp decline in mangrove area necessitates efficient monitoring via remote sensing. While Deep Neural Networks (DNNs) have excelled in segmentation tasks, their robustness remains inadequate. This limitation stems from the lack of theoretical guarantees regarding the continuity of layer-by-layer discrete transformations, rendering models susceptible not only to man-made adversarial attacks but also to natural degradations. To address these vulnerabilities, this paper leverages Neural Ordinary Differential Equations (NODEs) to enhance the robustness of mangrove segmentation. We designed and integrated various NODE architectures, including a novel NODE-SE-Block inspired by adaptive feature recalibration, to achieve more stable feature representations. Crucially, our findings reveal that by employing an adversarial training framework based on known attacks, the NODE-integrated network demonstrates superior cross-domain robustness. It not only defends against malicious exploits but also exhibits significantly enhanced resilience toward natural degradations, such as Gaussian noise and sensor-induced artifacts. Experimental results on mangrove datasets verify that the proposed methodology provides a reliable and interference-resistant foundation for ecological management in mission-critical scenarios. Full article

The recent rapid growth of deep learning has significantly reshaped the landscape of computer vision, establishing itself as the preferred paradigm for various tasks. Deep learning methods have demonstrated superior performance compared to previous state-of-the-art machine learning techniques across various fields. This review provides a concise overview of artificial neural networks (ANNs) and some of the most significant deep learning architectures, such as recurrent neural networks (RNNs), generative adversarial networks (GANs) and radial basis function networks (RBFNs). This review not only outlines the historical context and structures of these architectures but also provides a sophisticated understanding of their applications across different computer vision domains. A rigorous and comprehensive overview of these architectures is discussed throughout this review, and an essential systematic comparative analysis based on specific benchmarking criteria is provided. While individual deep learning frameworks excel in distinct domains, selecting the optimal architecture requires a balanced trade-off between algorithmic complexity, computational overhead, data dependencies, and structural interpretability. An intuitive and holistic benchmarking process synthesizes the core characteristics, technical configurations, operational constraints, and developmental pathways toward Explainable AI (XAI) and Green AI sustainability for the examined architectures (ANNs, RNNs, LSTMs, GANs, and RBFNs). Additionally, in this work the advantages and limitations of these architectures are discussed. Furthermore, an investigation of their applications in diverse computer vision tasks is carried out. Full article

The intelligent identification of grouting defects in grouted sleeves in prefabricated structures is critical for maintaining structural integrity. However, current deep learning-based identification methods face limitations, including insufficient model adaptability and the difficulty of obtaining labeled data. Models trained on one domain struggle to generalize to others due to differences in data distributions, making these methods challenging to apply in real-world scenarios. To address this engineering challenge, this paper investigates the applicability of maximum mean discrepancy-based domain adaptation (MMD-based DA) and domain adversarial training (DAT) approaches for cross-domain grouting defect identification. Acceleration signals collected by accelerometers near the grouted sleeves are used as the model input. The model’s ability to generalize across domains is evaluated by training on labeled data from one working condition and testing its performance on other working conditions using only unlabeled data. And these methods are compared with traditional Convolutional Neural Networks (CNNs). Experiments were conducted on a two-layer prefabricated frame structure. The experimental results demonstrated the effectiveness of the MMD-based DA method in improving the accuracy and robustness of defect identification across different domains, with the use of unlabeled data. Full article

Motor imagery (MI)-based brain–computer interfaces (BCIs) have led to great interest as a result of their potential use in neurorehabilitation, assistive robotics, and human–computer interaction. However, decoding electroencephalographic (EEG) signals with high accuracy continues to be a difficult task due to the weak signal-to-noise ratio, differences among subjects, and the complicated temporal–spectral–spatial neural dynamics. Deep learning methods recently developed, such as convolutional neural networks, recurrent architectures, graph neural networks, and adversarial transfer learning, have enhanced MI decoding performance, yet many models are still concentrating on a single representation domain or they need costly adaptation phases in terms of computation. To tackle these shortcomings, we present NeuroCrossNet, a unified tri-modal deep learning model that is able to learn the temporal, spectral, and spatial EEG features jointly for robust and calibration-free MI decoding. The suggested network combines a Temporal HyperMixer Block for capturing long-range temporal dependencies, a wavelet transformer for learning localized time–frequency representation, and a Graph Attention Network for EEG topology-aware spatial reasoning. Additionally, a Dynamic Residual Attention Gate (DRAG) has been developed to adaptively merge heterogeneous feature streams, and a compact subject-aware normalization (SAN) method enhances cross-subject generalization without the use of labeled target-domain calibration data. Our proposed model was tested following the rigorous leave-one-subject-out (LOSO) approach on BCI Competition IV-2a and High-Gamma datasets. NeuroCrossNet reached a classification accuracy of 91.30%, surpassing several strong benchmark methods, including CNN-LSTM, EEGNet, DeepConvNet, spectral CNN, and graph-based EEG decoding frameworks. Furthermore, a large number of ablation studies reveal that the integration of temporally, spectrally, and spatially complementary representations considerably boosts robustness and inter-subject consistency. Full article

Aiming at the problems of extremely scarce measured samples and significant domain shift between simulated and measured data in automatic target recognition (ATR) of air targets for spaceborne radar, this paper proposes an inverse synthetic aperture radar (ISAR) image recognition method for air targets combining physics-driven data augmentation guided by detection prior information with domain adversarial transfer learning. First, the mapping relationship between scattering point projection and ISAR images is established by using the target 3D point cloud and radar observation geometric priors, and a 2D sinc kernel function is introduced for energy distribution rendering. Then, under the unsupervised transfer learning paradigm, aiming at the distribution inconsistency between augmented data (source domain) and unlabeled simulated data (target domain), this paper designs a cross-domain recognition task experiment including six types of typical aircraft targets, and compares the cross-domain recognition performance of three transfer learning methods (model fine-tuning, deep domain confusion (DDC) and domain-adversarial neural networks (DANN)) on the target domain. Meanwhile, t-distributed stochastic neighbor embedding (t-SNE) visualization is used to analyze the feature distribution alignment ability of the models. Simulation experiments show that the DANN model with a dynamic inversion coefficient introduced in the gradient reversal layer (GRL) achieves a recognition accuracy of 99.5% on the unlabeled target domain, which is significantly superior to the model fine-tuning and DDC methods. Moreover, it makes the feature distributions of source and target domain samples highly overlapping, and maintains a strong inter-class discriminability while eliminating the domain shift. The proposed scheme provides a physically interpretable and robust technical path for few-shot radar target image recognition. Full article

The remarkably developed graph neural networks (GNNs) are extensively applied to specific tasks in online social networks (OSNs), especially in the vital domain of social trust. Meanwhile, the vulnerability of GNN applied in trust assessment can be exposed leveraging the deployment of subtly designed adversarial attacks. However, the predominant adversarial attack strategies targeting GNN are manipulating graph structure, which is not well-suited for social trust prediction tasks. In this article, we craft a novel black-box attack strategy, T-Attack, aimed at trust evaluation tasks, without tampering with the network structure of the specific trust prediction models. Specifically, a surrogate model is initially established to replicate trust prediction models based on GNN. The attack strategy on the surrogate model is formulated by adding unnoticed perturbations to user features related to network structure and manipulating the existing trust rating based on prior knowledge of social trust propagation, thereby avoiding a traditional attack against the GNN-based trust prediction model via modifying graph structure. By leveraging transferable attacks, our attack strategy can also distort the predictions of GNN-based trust prediction models. Through implementing extensive experiments in untargeted attack scenarios, we demonstrate the predictive performance of our crafted surrogate model and verify the effectiveness of the attack strategy on various GNN-based trust prediction models. Full article

Vision-based fire detection is highly sensitive to domain shifts between indoor and outdoor scenes, which often degrades the generalization of supervised models trained on a single domain. To study this problem, the Fire Detection Dataset is curated from multiple public sources as a large-scale benchmark for cross-domain fire and smoke recognition. Cross-domain deployment faces two main challenges: substantial appearance variations in fire and smoke, and highly diverse negative classes that can easily trigger false alarms. To address these issues, a tailored cross-domain framework is studied by combining adversarial alignment and discrepancy-based statistical alignment to learn more domain-invariant features and mitigate negative transfer. Experimental results show that domain adaptation substantially improves target-domain generalization over weak alignment baselines. In particular, Domain-Adversarial Neural Networks (DANN) achieve 89.44% accuracy on Indoor → Outdoor and 79.10% on Outdoor → Indoor, while Multi-Kernel Maximum Mean Discrepancy (MK-MMD) attains the best fire-class F1-score of 78.04% on Outdoor → Indoor. These results highlight the value of domain alignment for improving robust fire detection across heterogeneous deployment environments. Full article

Background/Objectives: Adversarial domain adaptation methods are widely used in EEG-based emotion recognition to reduce the influence of individual differences and the non-stationary characteristics of electroencephalogram (EEG) signals. Most existing methods employ binary domain discriminators to align source and target domains at the global distribution level. However, such strategies often neglect the potential multimodal structure of emotional EEG data and the asymmetric emotional processing characteristics of the left and right hemispheres. To address these issues, this study proposes a Bi-Hemispheric Adversarial Domain Adaptation Neural Network (BiHADA) for EEG-based emotion recognition. Methods: In the proposed BiHADA framework, the conventional binary domain discriminator is extended into a multimodal discriminator by incorporating the label structure information of source-domain data into the domain discrimination process. This design encourages features belonging to the same emotional category to be aligned across domains and promotes positive knowledge transfer. In addition, dual adversarial domain adaptation branches are constructed to model the left and right hemispheres separately, enabling the network to capture hemisphere-specific emotional representations. Furthermore, discriminator-derived perplexity is introduced to evaluate the distribution alignment quality of target samples and to adaptively determine the weights of the corresponding hemisphere classifiers, thereby reducing the influence of poorly aligned samples during the final decision stage. Results: Experiments on the SEED dataset show that BiHADA achieves classification accuracies of 86.82% and 92.71% in cross-subject and cross-session tasks, respectively. These results demonstrate that the proposed method can effectively improve the transferability and discriminability of EEG emotional features under different domain adaptation scenarios. Conclusions: The proposed BiHADA method enhances EEG-based emotion recognition by jointly considering class-structure-guided domain alignment, hemispheric functional asymmetry, and branch-wise adaptation quality. The results suggest that incorporating source-domain label structure and hemisphere-specific adaptation can improve cross-domain EEG emotion recognition performance. Full article

An ill-posed permittivity inversion problem is encountered in borehole radar (BHR) applications within stratified media due to a highly nonlinear forward relation, insufficient statistical coverage under data-limited conditions, strong noise contamination, and limited borehole observation geometry, which together cause instability and blurred boundaries. To address these challenges, a stratified media oriented conditional generative adversarial network for permittivity inversion, termed StratGAN, is proposed. BHR waveform data are used as the conditional input, and the complex mapping from time domain waveforms to depth domain permittivity distributions is learned end to end through conditional adversarial training between a generator and a discriminator, jointly constrained by a composite loss. During training, statistical characteristics of layered structures are learned from real samples by the discriminator, and adaptive feedback is provided as a data-driven loss to suppress spurious structures and boundary ambiguity. WGAN-GP is adopted and combined with a patch-based local discrimination mechanism to reinforce high-frequency details and geometric boundary consistency, thereby reducing the over-smoothing tendency of conventional CNNs. In addition, geometric consistency of inversion results is improved in an end-to-end manner without relying on complicated velocity analysis. Quantitative evaluations on simulated and measured datasets indicate that, compared with an architecture-matched convolutional neural network (CNN) and the baseline model GPRNet, StratGAN achieves overall better performance in terms of mean absolute error, coefficient of determination, and structural similarity metrics, and layered interfaces and anomaly boundaries are more effectively recovered. For the controlled measured data, the coefficient of determination ($R^2$) is improved to 0.9533 by StratGAN, whereas a value of 0.5598 is obtained by GPRNet. These results indicate the potential of StratGAN to enhance the reliability and structural fidelity of BHR permittivity inversion under limited-sample conditions, and preliminary evidence is provided for its practical applicability under controlled measured conditions. Full article

Inter-turn short-circuit faults (ITSC) in the stator winding of large synchronous machines are among the most critical failures in power systems and may lead to severe insulation damage and unplanned outages. At the same time, such faults, due to their nature in critical industrial scenarios, make it difficult to collect sufficiently rich labeled datasets for data-driven and deep-learning-based diagnostic methods. Training diagnostic models purely on simulated signals often results in a severe domain shift between the digital twin and the physical machine due to nonlinearities, mechanical noise, and measurement imperfections, causing a significant degradation of performance when the model is deployed in practice. This paper proposes a hybrid diagnostic framework that combines a nonlinear physics-based digital twin of a synchronous machine, formulated using an extended Park’s transformation model with a dedicated fault loop, with a Domain-Adversarial Neural Network (DANN) driven by a minimal physics-guided feature vector composed of the 100 Hz and 200 Hz harmonic amplitudes of the excitation current. Simulated data from the digital twin are used as a labeled source domain, whereas test-bench measurements of the excitation current form an unlabeled target domain, enabling unsupervised sim-to-real transfer of the stator fault resistance. The proposed architecture achieves accurate regression of the stator fault-loop resistance on a laboratory machine without any labeled measurements of real faults. Experimental results demonstrate Mean Absolute Error (MAE) below 3% across the investigated fault severity range, significantly outperforming baseline approaches that lack domain adaptation. The industrial significance of this approach lies in its potential to facilitate a transition from reactive to predictive maintenance. By enabling early-stage detection, the framework allows power plant operators to avoid catastrophic failures and significantly reduce exceptionally high costs associated with unplanned outages and cascading grid disturbances. Full article

Accurate recognition of Line-of-Sight (LOS) and Non-Line-of-Sight (NLOS) signals is crucial for mitigating positioning errors and improving the positioning performance of Ultra-Wideband (UWB) localization systems. Current NLOS identification methods are limited to the specific measurement environments and fail to exhibit effective cross-domain adaptability, being unable to generalize to unseen environments. To address these challenges, we propose a novel NLOS identification strategy based on a Domain-Adversarial Neural Network (DANN). Firstly, aiming at the problem that traditional feature extraction methods fail to capture the deep nonlinear characteristics of Channel Impulse Response (CIR) data, we develop a CNN-DAE-MLP-Attention (CDM) hybrid model for high-quality channel feature extraction, which takes both raw CIR data and handcrafted channel features into account. Secondly, we integrate the CDM model into the DANN framework by replacing its original shallow feature extraction module to further propose the CDMD algorithm; by combining the robust feature representation capability of CDM with the excellent domain adaptation capability of DANN, the proposed CDMD algorithm achieves enhanced performance in cross-domain LOS/NLOS identification. Finally, the effectiveness of the proposed algorithm is verified using measured data from different scenarios. Results demonstrate that the proposed algorithm possesses strong generalization ability. For cross-domain NLOS recognition from underground parking garage to corridor and underground parking garage to lobby, the proposed method achieves accuracies of 77.00% and 72.84%, respectively. Moreover, the results indicate that only a limited number of target-domain samples are sufficient for the model to achieve accurate cross-domain transfer. Full article

Modern neural networks have achieved remarkable success in visual recognition; however, due to their sensitivity to domain shifts, Unsupervised Domain Adaptation (UDA) remains an open research problem. A key reason for this limitation is that source-trained models rely primarily on texture, lacking the explicit geometric information required for object recognition. To overcome this problem, we introduce CoDA, an object-centric learning framework inspired by infant cognitive development, specifically the process of object individuation. By introducing a geometric prior, our approach employs a physically grounded generation pipeline that uses a textureless “Sculpture Mode” and object isolation to complement textural information with 3D geometric features, capturing shape information that is often ignored during training. To enable robust training from scratch, we further integrate two control mechanisms: a Network Stability Scheduler to orchestrate training progression based on convergence stability, and a Dynamic Top-K Pseudo-Labeling strategy that adapts confidence thresholds for each individual class. Extensive evaluations on three real-world target datasets (VegFru, Fruits-262, and Open Images v7) demonstrate that CoDA, trained on a source dataset of just 12,000 synthetic images, achieves comparable results to (and in specific domains surpasses) ImageNet-pretrained models (leveraging 1.2 million images), significantly outperforming state-of-the-art adversarial and semi-supervised domain adaptation methods. Full article

With increasing port automation and operational intensity, the gearboxes of gantry cranes widely used in bulk cargo terminals are prone to bearing and gear failures under prolonged heavy loads, intense vibrations, and complex operating conditions. Since fault samples often exhibit imbalanced distributions, this imposes two higher requirements on diagnostic methods—first, the ability to effectively address sample imbalance and, second, the capability to simultaneously identify multiple fault categories. To address these challenges, this paper proposes a joint diagnostic method integrating an improved Conditional Wasserstein Generative Adversarial Network with Gradient Penalty (CWGAN-GP) and Multi-Task Learning (MTL). First, the modified CWGAN-GP performs conditional augmentation for minority fault classes, evaluating synthetic sample authenticity and diversity through multiple metrics. Subsequently, a multi-channel diagnostic network is constructed, in which vibration signals are fed into two parallel sub-networks: time–frequency features are extracted from the Short-Time Fourier Transform (STFT)-based time–frequency representations via a residual-block Convolutional Neural Network (CNN), while temporal features are captured from the raw time-domain signal using a Bidirectional Long Short-Term Memory (Bi-LSTM) with an attention mechanism. An attention fusion layer then integrates these two feature types, enabling joint classification of bearings and gears within a multi-task learning framework. Experimental validation on public gearbox datasets and port gantry crane gearbox datasets demonstrates that this method achieves an average diagnostic accuracy exceeding 97%. The proposed method reduces the impact of class imbalance, thereby improving the accuracy and stability of multi-task fault identification. Full article