Polarimetric Synthetic Aperture Radar (PolSAR) images have emerged as an important data source for land cover classification research due to their all‐weather, all‐day monitoring capabilities. Deep learning‐based classification methods have recently gained significant attention in PolSAR image classification since they have demonstrated excellent performance in the computer vision field. However, the main issue with deep learning‐based methods is that they require large amounts of training data. Additionally, the scarcity of labeled data is a significant challenge in the PolSAR image field. Therefore, in this article, we proposed an advanced semisupervised deep self‐training algorithm for PolSAR image classification, which utilized both labeled and unlabeled data in a semisupervised way. Then, a training optimization method and a high‐confidence sample selection strategy are proposed by integrating consistency regularization. In addition, to achieve stronger feature extraction capabilities, we designed a deep learning‐based classifier that combines residual blocks with an efficient multiscale attention module. We have conducted experiments on three popular real PolSAR datasets: 1989 Flevoland, 1991 Flevoland, and Oberpfaffenhofen. The classification results on these datasets demonstrated that the proposed method outperforms several other comparison algorithms, with overall accuracy up to 99.3%, 99.15%, and 94.12%, respectively. These results demonstrated the effectiveness of the proposed method for PolSAR image classification.

The advancement of intelligent systems, particularly in domains such as natural language processing and autonomous driving, has been primarily driven by deep neural networks (DNNs). However, these systems exhibit vulnerability to adversarial attacks that can be both subtle and imperceptible to humans, resulting in arbitrary and erroneous decisions. This susceptibility arises from the hierarchical layer‐by‐layer learning structure of DNNs, where small distortions can be exponentially amplified. While several defense methods have been proposed, they often necessitate prior knowledge of adversarial attacks to design specific defense strategies. This requirement is often unfeasible in real‐world attack scenarios. In this paper, we introduce a novel learning model, termed “immune” learning, known as adversarial‐resilient deep symbolic tree (ARDST), from a neurosymbolic perspective. The ARDST model is semiparametric and takes the form of a tree, with logic operators serving as nodes and learned parameters as weights of edges. This model provides a transparent reasoning path for decision‐making, offering fine granularity, and has the capacity to withstand various types of adversarial attacks, all while maintaining a significantly smaller parameter space compared to DNNs. Our extensive experiments, conducted on three benchmark datasets, reveal that ARDST exhibits a representation learning capability similar to DNNs in perceptual tasks and demonstrates resilience against state‐of‐the‐art adversarial attacks.

Existing application‐layer distributed denial of service (AL‐DDoS) attack detection methods are mainly targeted at specific attacks and cannot effectively detect other types of AL‐DDoS attacks. This study presents an application‐layer protocol communication model for AL‐DDoS attack detection, based on the explicit duration recurrent network (EDRN). The proposed method includes model training and AL‐DDoS attack detection. In the AL‐DDoS attack detection phase, the output of each observation sequence is updated in real time. The observation sequences are based on application‐layer protocol keywords and time intervals between adjacent protocol keywords. Protocol keywords are extracted based on their identification using regular expressions. Experiments are conducted using datasets collected from a real campus network and the CICDDoS2019 dataset. The results of the experiments show that EDRN is superior to several popular recurrent neural networks in accuracy, F 1, recall, and loss values. The proposed model achieves an accuracy of 0.996, F 1 of 0.992, recall of 0.993, and loss of 0.041 in detecting HTTP DDoS attacks on the CICDDoS2019 dataset. The results further show that our model can effectively detect multiple types of AL‐DDoS attacks. In a comparison test, the proposed method outperforms several state‐of‐the‐art approaches.

This paper explores a new online learning problem where the data streams are generated from an over-time varying feature space, in which the random variables are of mixed data types including Boolean, ordinal, and continuous. The crux of this setting lies in how to establish the relationship among features, such that the learner can enjoy 1) reconstructed information of the missed-out old features and 2) a jump-start of learning new features with educated weight initialization. Unfortunately, existing methods mainly assume a linear mapping relationship among features or that the multivariate joint distribution could be modeled as Gaussians, limiting their applicability to the mixed data streams. To fill the gap, we in this paper propose to model the complex joint distribution underlying mixed data with Gaussian copula, where the observed features with arbitrary marginals are mapped onto a latent normal space. The feature correlation is approximated in the latent space through an online EM process. Two base learners trained on the observed and latent features are ensembled to expedite convergence, thereby minimizing prediction risk in an online setting. Theoretical and empirical studies substantiate the effectiveness of our proposed approach. Code is released in https://github.com/xiexvying/OVFM.