With the continuous development of network technology, the diversity of network traffic constantly increased (intra-class diversity). Nevertheless, the boundary between malicious and benign actions became even ambiguous (inter-class similarity), causing lots of false detection and hindering the further optimization of the detection model. Focusing on challenges brought by intra-class diversity and inter-class similarity, we proposed a novel approach to enhance intrusion detection based on contrastive learning, which can make the right decision while disentangling samples from different classes. First, to bridge the gap when applying contrastive learning to intrusion detection data, we proposed a heuristic method to build contrastive tasks based on random masking of network packet sequences, which can reflect semantic relationships among samples. Then contrastive loss can be calculated to measure the inter-class and intra-class distances. Second, contrastive cross-entropy loss was proposed, which was a combination of contrastive loss and classification loss. Together with a dual branch deep structure, we can optimize the detection and sample distance requirements at the same time. Thirdly, experiments were conducted on diverse real-world and benchmark datasets using different model architectures under various parameter settings. Results on real-world dataset showed that our methods could stable experience a 5% increase in accuracy, and an 8% improvement in detection rate on those easily misdetected scenarios. To verify the method’s effectiveness on different traffic representations, we further conducted experiments on NSL-KDD and UNSW-NB15, which achieved a 7% accuracy improvement on NSL-KDD and a 6% accuracy improvement on UNSW-NB15. Extensive comparison with state of art intrusion detection models in recent five years showed that the proposed methods could effectively improve the accuracy of detection models.

Eosinophilic pneumonia (EP) is a rare but noteworthy adverse effect linked to dupilumab, an interleukin-4 (IL-4) and IL-13 inhibitor used in the managing atopic diseases. The underlying mechanisms, potential predisposing factors, clinical characteristics, and optimal management strategies for dupilumab-induced EP remain unclear. We report a 71-year-old patient who developed acute EP after the first 600-mg dose of dupilumab. Eosinophils (EOSs) were also transiently increased (up to 1,600 cells/μl). After the acute EP was effectively treated with glucocorticoids, dupilumab treatment was continued. Rash, itching, and immunoglobulin E levels continued to decrease in the patient, and no further pulmonary adverse events occurred. We combined this case with a literature review of nine articles and analyzed data from 93 cases reported in the FDA Adverse Event Reporting System (FAERS) database of patients developing EP after dupilumab use. Our findings imply that dupilumab may induce EP, particularly in individuals over 45 years old, those with a history of respiratory diseases, and those who have previously used inhaled or systemic steroids. Vigilance is required, especially when there is a persistent elevation in peripheral blood EOSs during treatment. Although steroid treatment can effectively manage EP, more data are needed to determine the safety of resuming dupilumab treatment after controlling pneumonia.

Cloud Virtual Private Server (VPS) services provide the chance of rapid deployment of anonymous proxy services, becoming an important part of many anonymous proxy solutions. The anonymous system represented by ShadowSocks (SS), through proxy services deployed on VPSs provided by different cloud service providers, has become an important mean for illegal network activists to engage in illegal network activities such as cyber-attacks and darknet transactions. It is difficult for local network administrators to supervise SS traffic from the cloud. While from the local network, the task faces the challenges of Invisible Negotiation Process and Data Transparent Transmission. In this paper, we present a novel SS detection method based on flow context and host behavior. The method can not only accurately identify SS flows, but also be applicable to a large-scale network environment. In this method, we extract 12-dimensional features from three aspects: the relationship between flows, hosts' flow behavior, and hosts' DNS behavior to build the detection model. Among them, the four features about flow burst and the feature of unassociated domain names' number are innovatively proposed in this paper. Moreover, the big data statistical and association techniques are used in the method. To verify the effectiveness of the method, we first built a real SS running environment based on the campus network and two VPSs on two different public cloud platforms. Moreover, we conduct a series of experiments on the NTCI-BDP data platform which is a big data platform built by our team. The experimental results show that our method achieves 93.43% accuracy on experimental data sets and can effectively identify SS traffic.

The success of a detection model depends heavily on feature engineering. Deep learning has been successfully applied in numerous research fields as a universal representation learning method. However, the heterogeneity of flow-level communication data obstructs the application of deep learning to communication representation learning, and research on this problem is still lacking. To cope with this problem, we propose a heterogeneous communication data-encoding approach to extract fixed-size encoding data to apply deep learning to heterogeneous communication data by preserving the spatiotemporal characteristics of the data. Then, we propose a feature extractor based on deep learning to automatically learn hierarchical and robust communication representations without expert knowledge. We show that the proposed approach can replicate and optimize the key steps of feature engineering well and learn hierarchical representations directly from heterogeneous communication data. Moreover, compared with features extracted with principal component analysis (PCA), manifold learning and manually crafted methods, the features extracted by deep learning are more robust and are characterized by their better adaptability to various classifiers and datasets. To the best of our knowledge, the initial work here is the first to apply deep learning techniques to heterogeneous flow-level data; consequently, the heterogeneous communication data processing method can provide technical means for the application of deep learning in other communication-related research fields.

Antineutrophil cytoplasm antibody (ANCA)-associated vasculitis (AAV) is a pauci-immune necrotizing vasculitis that involves small vessels. Herein, we report an extremely rare case of rifampicin (RFP)-induced AAV. A 42-yearold female was transferred to the West China Hospital due to cough with phlegm for 3 months, fever for 1 month, and fatigue for 2 weeks. The patient was diagnosed with pulmonary tuberculosis (TB) and received anti-TB treatment with isoniazid, RFP, ethambutol, and pyrazinamide (PZA) at her local hospital. After 5 days of anti-TB treatment, her creatinine level rose to 420.2 μmol/L from a normal level prior to anti-TB treatment. Serum proteinase 3 (PR3)-ANCA was positive. After discontinuing the anti-TB drugs and administering protective renal treatment, her renal function improved, whereas PR3-ANCA remained positive. With RFP rechallenge after transfer to our hospital, the patient developed oliguria. Her urine volume increased gradually after RFP was discontinued 3 days later. Therefore, RFPinduced AAV was suspected. Eventually, the patient received prednisone and anti-TB therapy, including isoniazid, ethambutol, PZA, and moxifloxacin. After 2 months, PZA was discontinued. During 6 months of normal, and PR3-ANCA became negative at 4 months. This outcome is characteristic of RFP-induced AAV.

Caenorhabditis elegans is a useful model organism for combining multiple imaging, genetic, and biochemical methodologies to gain more insight into the biological function of specific proteins. Combining both biochemical and genetic analyses can lead to a better understanding of how a given protein may function within the context of a network of other proteins or specific pathway. Here, we describe a protocol for the biochemical isolation of serpin-interacting proteins using affinity purification and proteomic analysis. As the knowledge of in vivo serpin interacting partners in C. elegans has largely been obtained using genetic and in vitro recombinant protein studies, this protocol serves as a complementary approach to provide insight into the biological function and regulation of serpins.