Abstract
Given the gradual intensification of the current network security situation, malicious attack traffic is flooding the entire network environment, and the current malicious traffic detection ...model is insufficient in detection efficiency and detection performance. This paper proposes a data processing method that divides the flow data into data flow segments so that the model can improve the throughput per unit time to meet its detection efficiency. For this kind of data, a malicious traffic detection model with a hierarchical attention mechanism is also proposed and named HAGRU (Hierarchical Attention Gated Recurrent Unit). By fusing the feature information of the three hierarchies, the detection ability of the model is improved. An attention mechanism is introduced to focus on malicious flows in the data flow segment, which can reasonably utilize limited computing resources. Finally, compare the proposed model with the current state of the method on the datasets. The experimental results show that: the novel model performs well in different evaluation indicators (detection rate, false-positive rate,
F
-score), and it can improve the performance of category recognition with fewer samples when the data is unbalanced. At the same time, the training of the novel model on larger datasets will enhance the generalization ability and reduce the false alarm rate. The proposed model not only improves the performance of malicious traffic detection but also provides a new research method for improving the efficiency of model detection.
Self-assembling natural drug hydrogels formed without structural modification and able to act as carriers are of interest for biomedical applications. A lack of knowledge about natural drug gels ...limits there current application. Here, we report on rhein, a herbal natural product, which is directly self-assembled into hydrogels through noncovalent interactions. This hydrogel shows excellent stability, sustained release and reversible stimuli-responses. The hydrogel consists of a three-dimensional nanofiber network that prevents premature degradation. Moreover, it easily enters cells and binds to toll-like receptor 4. This enables rhein hydrogels to significantly dephosphorylate IκBα, inhibiting the nuclear translocation of p65 at the NFκB signalling pathway in lipopolysaccharide-induced BV2 microglia. Subsequently, rhein hydrogels alleviate neuroinflammation with a long-lasting effect and little cytotoxicity compared to the equivalent free-drug in vitro. This study highlights a direct self-assembly hydrogel from natural small molecule as a promising neuroinflammatory therapy.
For the current mainstream DGA domain name detection methods, scalars are almost used to represent numerical features, resulting in the loss of the spatial feature information of domain name ...characters. This paper proposes a sequence capsule network based on the
k
-means routing algorithm, LSTM-CapsNet, which only uses DGA domain name text information for detection. The model uses a bidirectional LSTM unit to extract basic features for the capsule network and uses the
k
-means algorithm to cluster vector features to implement routing functions. In order to verify the proposed LSTM-CapsNet model, data from two different sources are collected to ensure the reliability of the experiment, covering the DGA domain name dataset from the real network defined as Real-Dataset, and the DGA domain name obtained through the domain name generation algorithm is defined as Gen-Dataset. The current DGA domain name detection method of state-of-the-art proposed by researchers is compared and tested on two data sets. The experimental results show that the proposed model has achieved 99.17% and 97.75% of the
F-score
evaluation indicators in the DGA domain name recognition of the two datasets; at the same time, the recognition of the DGA domain name family has been very competitive. Compared with the existing DGA domain name family classification model, the F-score value of the proposed model exceeds 89% in Gen-Dataset multi-class recognition. This model not only improves the ability of DGA domain name recognition and DGA domain name family recognition but also has an outstanding ability to find real-time aspects in model testing.
Chelerythrine (CH) and ethoxychelerythrine (ECH) are chemical reference substances for quality control of Chinese herbal medicines, and ECH is the dihydrogen derivative of CH. In this study, their ...fluorescence and absorption spectra, as well as their structural changes in different protic solvents were compared. It was observed that their emission fluorescence spectra in methanol were almost the same (both emitted at 400 nm), which may be attributed to the nucleophilic and exchange reactions of CH and ECH with methanol molecules with the common product of 6-methoxy-5,6-dihydrochelerythrine (MCH). When diluted with water, MCH was converted into CH, which mainly existed in the form of positively charged CH+ under acidic and near-neutral conditions with the fluorescence emission at 550 nm. With the increase of pH value of the aqueous solution, CH+ converted to 6-hydroxy-5,6-dihydrochelerythrine (CHOH) with the fluorescence emission at 410 nm. The fluorescence quantum yields of MCH and CHOH were 0.13 and 0.15, respectively, and both the fluorescence intensities were much stronger than that of CH+. It is concluded that CH and ECH can substitute each other in the same protic solvent, which was further verified by high-performance liquid chromatography. This study will help in the investigation of structural changes of benzophenanthridine alkaloids and will provide the possibility for the mutual substitution of standard substances in relevant drug testing.
In this work, the origins for the spectral difference between two isoflavones, formononetin (F) and ononin (FG), are revealed via a comparison study of the fluorescence molecular structure. The ...fluorescence enhancement of FG in hot alkaline conditions is reported for the first time. For F, there is almost no fluorescence under acidic conditions, but when the pH is >4.8, its fluorescence begins to increase due to the deprotonation of 7-OH. Under a pH between 9.3 and 12.0, the anionic form of F produces a strong and stable fluorescence. The fluorescence quantum yield (Yf) of F is measured to be 0.042. FG shows only weak fluorescence in aqueous solutions under a wide range of pH until it is placed in hot alkaline solutions, which is attributed to the cleavage reaction of the γ-pyrone ring in FG. The Yf of FG is determined to be 0.020. Based on the fluorescence sensitization methods of F and FG, the quantitative analysis and detection of two substances can be realized. The limit of the detections for F and FG are 2.60 ng·mL
and 9.30 ng·mL
, respectively. The linear detection ranges of F and FG are 11.7~1860 ng·mL
and 14.6~2920 ng·mL
, respectively. Although the structural relationship between F and FG is glycoside and aglycone, under hot alkaline conditions, the final products after the cleavage and hydrolysis reactions are essentially different. The different fluorescence characteristics between F and FG pave a way for further identification and a quantitative analysis of the corresponding components in Chinese herbal medicine.
Our previous study demonstrated that the methyl-CpG-binding domain protein 2 (MBD2) mediates vancomycin (VAN)-induced acute kidney injury (AKI). However, the role and regulation of MBD2 in septic AKI ...are unknown. Herein, MBD2 was induced by lipopolysaccharide (LPS) in Boston University mouse proximal tubules (BUMPTs) and mice. For both in vitro and in vivo experiments, we showed that inhibition of MBD2 by MBD2 small interfering RNA (siRNA) and MBD2-knockout (KO) substantially improved the survival rate and attenuated both LPS and cecal ligation and puncture (CLP)-induced AKI, renal cell apoptosis, and inflammatory factor production. Global genetic expression analyses and in vitro experiments suggest that the expression of protein kinase C eta (PKCη), caused by LPS, is markedly suppressed in MBD2-KO mice and MBD2 siRNA, respectively. Mechanistically, chromatin immunoprecipitation (ChIP) analysis indicates that MBD2 directly binds to promoter region CpG islands of PKCη via suppression of promoter methylation. Furthermore, PKCη siRNA improves the survival rate and attenuates LPS-induced BUMPT cell apoptosis and inflammatory factor production via inactivation of p38 mitogen-activated protein kinase (MAPK) and extracellular signal-regulated kinase (ERK)1/2, which were further verified by PKCη siRNA treatment in CLP-induced AKI. Finally, MBD2-KO mice exhibited CLP-induced renal cell apoptosis and inflammatory factor production by inactivation of PKCη/p38MAPK and ERK1/2 signaling. Taken together, the data indicate that MBD2 mediates septic-induced AKI through the activation of PKCη/p38MAPK and the ERK1/2 axis. MBD2 represents a potential target for treatment of septic AKI.
Display omitted
MBD2 played a pivotal role in septic AKI. Mechanistically, MBD2 activated PKCη/p38MAPK and the ERK1/2 axis to induce renal cell apoptosis and inflammation factors production, respectively. The data suggested that MBD2 may be a potential target for septic AKI.
Dichlorodiphenyltrichloroethane (DDT) is a typical organic compound characterized by high bioaccumulability, toxicity, and persistence in the environment. To analyze the distribution and sources of ...DDTs in Poyang Lake, which is an important congregation site for migratory birds, the topsoils from five typical wetlands were sampled to evaluate the ecological threat posed by DDTs to organisms. The results show that as much as 56.1 % of the DDTs detected in this study comprises dichlorodiphenyldichloroethylene (DDE), the aerobic metabolism of DDT. The o,p′-DDT:p,p′-DDT ratio was higher than 0.2, which suggests that there was fresh influx of DDT from the pesticide. These results indicate that DDE was the main component among the metabolisms of DDTs and that the usage of dicofol might introduce DDT into the environment of Lake Poyang in a stealth form. However, an ecological risk assessment shows that the DDTs content in this region poses a low ecological risk.
In recent years, the application of Graph Neural Networks (GNNs) in fraud detection has gained considerable attention. GNNs have demonstrated their efficacy in leveraging the abundant relational ...information inherent in graph-structured data for such tasks. However, despite the remarkable progress achieved thus far, several challenges still need to be addressed in the current GNN-based algorithms. On the one hand, GNNs exhibit limited performance when confronted with imbalanced label distribution between fraudsters and benign users. On the other hand, the embedding representations learned for nodes and their neighbors in the last layer are frequently processed in a simplistic manner, such as concatenation or averaging, which may compromise the performance of downstream tasks. To alleviate the above problems, we propose a novel imbalanced and interactive learning framework for fraud detection on multi-relation graphs (IMINF for short). Concretely, firstly, we design a novel neighbor sampler that can be trained using supervised contrastive learning. This sampler selects the most similar and consistent neighbors to update the target node's features, taking into account label information from multiple perspectives. Secondly, we introduce the learnable contrastive embedding and an improved relational aggregator to enhance the representation of the target node. Thirdly, we propose a new interactive learning module, which consists of explicit and implicit transformation layers, with the aim of capturing deep interactive relations between a target node and its neighbors. Additionally, we devise a feature mapping module prior to the relation aggregation step, transferring the raw input features to a latent feature subspace. Extensive experiments on two real-world fraud detection datasets demonstrate that the proposed model outperforms existing baselines across all evaluation metrics, especially for the Amazon fraud detection dataset.
Article comment generation is a new and challenging task in natural language processing, which has recently received much attention from researchers. In the article comment generation, there are ...apparent distinctions and different perspectives on the comments of a single article. However, current researches ignore the one-to-many relationship between articles and comments, resulting in a lack of diversity and coherence in generated comments. To solve this problem, a variational selection mechanism model (VSMM) is proposed in our research. In this model, we construct a Gaussian mixture prior network to capture a richer latent space and generate comments with more diversity and informativeness. At the same time, VSMM maps latent variables into different semantic spaces through the selection mechanism to capture one-to-many relationships. Then we introduce a discriminator to distinguish whether the selected content is consistent with the reference comment content, thus improving the coherence of the generated comments. In addition, a hierarchical encoder with attention is introduced in the VSMM model, which can effectively solve the problem of long document encoding. Furthermore, we propose a multi-category article comment dataset to align closely with practical applications. Experiments on three datasets demonstrate that VSMM outperforms existing state-of-the-art comment generation methods in terms of diversity in single and multiple comment generations. Moreover, VSMM can generate fluent, diverse, and coherent comments on multi-category and topic-rich datasets.