Malware Identification Method in Industrial Control Systems Based on Opcode2vec and CVAE-GAN.

Industrial Control Systems (ICSs) have faced a significant increase in malware threats since their integration with the Internet. However, existing machine learning-based malware identification methods are not specifically optimized for ICS environments, resulting in suboptimal identification performance. In this work, we propose an innovative method explicitly tailored for ICSs to enhance the performance of malware classifiers within these systems. Our method integrates the opcode2vec method based on preprocessed features with a conditional variational autoencoder-generative adversarial network, enabling classifiers based on Convolutional Neural Networks to identify malware more effectively and with some degree of increased stability and robustness. Extensive experiments validate the efficacy of our method, demonstrating the improved performance of malware classifiers in ICSs. Our method achieved an accuracy of 97.30%, precision of 92.34%, recall of 97.44%, and F1-score of 94.82%, which are the highest reported values in the experiment.

Expression of lymphocyte activation gene-3 on CD4+T cells is regulated by cytokine interleukin-18 in myasthenia gravis.

Myasthenia gravis (MG) is a T cell-dependent, B cell-mediated, and complement-dependent autoimmune disease. Lymphocyte activation gene-3 (LAG-3; CD223) is an immune checkpoint protein that plays an important role in maintaining autoimmune tolerance and homeostasis. To investigate the cytokine-regulated expression pattern of LAG-3, CD4+T cells were sorted from the peripheral blood of healthy volunteers by density gradient centrifugation and stimulated with various cytokines in vitro. The expression of membrane LAG-3 (mLAG-3), membrane a disintegrin and metallopeptidase domain10 (mADAM10) and membrane ADAM17 (mADAM17) on CD4+T cells was detected by flow cytometry; the concentration of soluble LAG-3 (sLAG-3) was detected by ELISA; and the relative expression of genes at the transcriptional level was detected by fluorescence quantitative RT-PCR (qRT-PCR). sLAG-3 levels were significantly increased in the peripheral plasma of AChR Ab-positive patients with MG compared to healthy volunteers, while the percentage of mLAG-3 expression on CD4+T lymphocytes in the peripheral blood of patients with MG was significantly reduced. IL-18 inhibited mLAG-3 levels on CD4+T cells in a concentration-dependent manner. Additionally, the concentration of sLAG-3 in the supernatant increased. After PHA and IL-18 stimulation, ADAM10 and ADAM17 also increased compared to those in the PHA-active group. Moreover, there were significant differences in the expression of mADAM10 and mADAM17 in CD4+T lymphocytes between patients with MG and healthy volunteers. These results suggest that IL-18 may regulate the expression pattern of mLAG-3 in CD4+T cells and sLAG-3 via ADAM10- and ADAM17-mediated pathways, thus affecting the immune effects of CD4+T cells. This study provides a preliminary exploration of the upstream regulatory molecules of the LAG-3 and IL-18/LAG-3 signalling pathways for potential targeted therapy of autoimmune diseases in the future.

Abnormal brain spontaneous neural activity in neuromyelitis optica spectrum disorder with neuropathic pain.

Background: Neuropathic pain is one of the most common symptoms in neuromyelitis optica spectrum disorder (NMOSD). Notwithstanding, its underlying mechanism remains obscure. Methods: The amplitude of low-frequency fluctuations (ALFF) metric was employed to investigate spontaneous neural activity alterations via resting-state functional magnetic resonance imaging (rs-MRI) data from a 3.0 T MRI scanner, in a sample of 26 patients diagnosed with NMOSD with neuropathic pain (NMOSD-WNP), 20 patients with NMOSD but without neuropathic pain (NMOSD-WoNP), and 38 healthy control (HC) subjects matched for age and sex without the comorbidity of depressive or anxious symptoms. Results: It was observed that patients with NMOSD-WNP displayed a significant ALFF decrease in the left amygdala and right anterior insula, relative to both patients with NMOSD-WoNP and HC subjects. Furthermore, ALFF values in the left amygdala were negatively correlated with the scores of the Douleur Neuropathique en 4 Questions and McGill Pain Questionnaire (both sensory and affective descriptors) in patients with NMOSD-WNP. Additionally, there were negative correlations between the ALFF values in the right anterior insula and the duration of pain and the number of relapses in patients with NMOSD-WNP. Conclusion: The present study characterizes spontaneous neural activity changes in brain regions associated with sensory and affective processing of pain and its modulation, which underscore the central aspects in patients with NMOSD-WNP. These findings might contribute to a better understanding of the pathophysiologic basis of neuropathic pain in NMOSD.