Cross-site scripting attack detection based on a modified convolution neural network.

Cross-site scripting (XSS) attacks are currently one of the most threatening network attack methods. Effectively detecting and intercepting XSS attacks is an important research topic in the network security field. This manuscript proposes a convolutional neural network based on a modified ResNet block and NiN model (MRBN-CNN) to address this problem. The main innovations of this model are to preprocess the URL according to the syntax and semantic characteristics of XSS attack script encoding, improve the ResNet residual module, extract features from three different angles, and replace the full connection layer in combination with the 1*1 convolution characteristics. Compared with the traditional machine learning and deep learning detection models, it is found that this model has better performance and convergence time. In addition, the proposed method has a detection rate compared to a baseline of approximately 75% of up to 99.23% accuracy, 99.94 precision, and a 98.53% recall value.

Serum Creatinine/Cystatin C Ratio as a Predictor of In-hospital Mortality in Patients Hospitalized with Acute Exacerbation of Chronic Obstructive Pulmonary Disease.

PURPOSE: Low serum creatinine/cystatin C ratio (CCR) is associated with unfavorable characteristics in patients with chronic obstructive pulmonary disease (COPD); however, the relationship between CCR and in-hospital mortality of patients with acute exacerbation of COPD (AECOPD) is unexplored. Our objective was to assess the value of CCR for predicting in-hospital mortality of patients hospitalized with AECOPD. METHODS: Patients with AECOPD (n = 597) were retrospectively enrolled. Patient's clinical characteristics and laboratory tests, including serum cystatin C and creatinine, were reviewed. The prediction value of CCR was evaluated using area under the receiver operating characteristic curve (AUC) values. Factors potentially impacting in-hospital mortality were investigated using univariate and multivariate logistic regression analyses. RESULTS: Mortality rate during hospitalization was 10.05%. CCR was lower in non-surviving vs. survived patients (41.67 vs. 61.52, P < 0.001). AUC value for CCR for in-hospital mortality prediction was 0.79 [95% confidence interval (CI) 0.73-0.85]. On multivariate logistic regression analysis, in-hospital mortality was strongly associated with CCR < 52.27 [odds ratio (OR) 6.23, 95% CI (3.00-12.92), P < 0.001], age ≥ 81 years [OR 2.97, 95% CI (1.20-7.37), P = 0.019], oxygenation index < 300 [OR 3.28, 95% CI (1.27-8.44), P = 0.014], CRP > 8 mg/L [OR 1.84, 95% CI (1.15-2.95), P = 0.012], and D-dimer > 500 ng/L [OR 5.19, 95% CI (1.51-17.79), P = 0.009]. CONCLUSIONS: CCR was significantly lower, and is a potential prognostic indicator, in patients with AECOPD who died during hospitalization.

Association between Central Serous Chorioretinopathy and Risk of Depression: A Population-Based Cohort Study.

PURPOSE: To investigate the association between central serous chorioretinopathy (CSC) and the risk of developing depression. The risk factors associated with depression in CSC patients were also assessed. METHODS: A population-based retrospective cohort study using the Taiwan National Health Insurance Research Database was conducted from the beginning of 2001 through the end of 2013. CSC patients and age- and gender-matched (1 : 4 matched) control subjects without CSC were enrolled in the study. Kaplan-Meier curves were generated to compare the cumulative hazard of subsequent depression between the CSC and control groups. A Cox regression analysis estimated the crude and adjusted hazard ratios (HRs) for depression. Risk factors leading to depression were investigated among the CSC patients. RESULTS: 25,939 CSC patients and 103,756 controls were enrolled in the study. The CSC group had a significantly higher cumulative hazard for depression compared to the control group (p value < 0.0001). The Cox regression model indicated that the CSC group had a significantly higher risk for depression (adjusted HR = 1.33). Within the CSC group, significant risk factors for depression included age, female gender, low income, first-onset CSC, peptic ulcer, and smoking. The recent use of steroids prior to CSC, by all routes of administration, also significantly increased the risk for depression. However, treatment of CSC did not significantly reduce the risk for depression. CONCLUSION: Patients with CSC are at significantly greater risk of developing depression. Among CSC patients, age, female gender, low income, first-onset CSC, peptic ulcer, smoking, and recent use of steroids prior to CSC were significant risk factors for depression.

Two frequent mutations associated with the classic form of propionic acidemia in Taiwan.

Propionyl-CoA carboxylase (PCC) is involved in the catabolism of branched chain amino acids, odd-numbered fatty acids, cholesterol, and other metabolites. PCC consists of two subunits, α and ß, encoded by the PCCA and PCCB genes, respectively. Mutations in the PCCA or PCCB subunit gene may lead to propionic acidemia. In this study, we performed mutation analysis on ten propionic acidemia patients from eight unrelated and nonconsanguineous families in Taiwan. Two PCCA mutations, c.229C→T (p.R77W) and c.1262A→C (p.Q421P), were identified in a PCCA-deficient patient. Six mutations in the PCCB gene, including c.-4156_183+3713del, c.580T→C (p.S194P), c.838dup (p.L280Pfs 11), c.1301C→T (p.A434V), c.1316A→G (P.Y439C), and c.1534C→T (p.R512C), were identified in seven PCCB-deficient families. The c.-4156_183+3713del mutation is the first known large deletion that affects the PCCB gene functions. Furthermore, the c.1301C→T and c.-4156_183+3713del mutations in the PCCB gene have not been reported previously. Clinical features demonstrated that these two frequent mutations are associated with low enzyme activity and a classic propionic acidemia phenotype.