• Journal of Information Processing Systems
• /
• v.15 no.3
• /
• pp.520-537
• /
• 2019

This paper proposes a system that can detect the data leakage pattern using a convolutional neural network based on defining the behaviors of leaking data. In this case, the leakage detection scenario of data leakage is composed of the patterns of occurrence of security logs by administration and related patterns between the security logs that are analyzed by association relationship analysis. This proposed system then detects whether the data is leaked through the convolutional neural network using an insider malicious behavior graph. Since each graph is drawn according to the leakage detection scenario of a data leakage, the system can identify the criminal insider along with the source of malicious behavior according to the results of the convolutional neural network. The results of the performance experiment using a virtual scenario show that even if a new malicious pattern that has not been previously defined is inputted into the data leakage detection system, it is possible to determine whether the data has been leaked. In addition, as compared with other data leakage detection systems, it can be seen that the proposed system is able to detect data leakage more flexibly.

• Clinical and Experimental Pediatrics
• /
• v.63 no.6
• /
• pp.219-225
• /
• 2020

Background: There is increasing concern that moderate preterm (32-33 weeks' gestation) and late preterm (34-36 weeks' gestation) birth may be associated with minor neurodevelopmental problems affecting poor school performance. Purpose: We explored the cognitive function, cognitive visual function, executive function, and behavioral problems at school age in moderate to late preterm infants. Methods: Children aged 7-10 years who were born at 32⁺⁰ to 36⁺⁶ weeks of gestation and admitted to the neonatal intensive care unit from August 2006 to July 2011 at the National Health Insurance Service Ilsan Hospital were included. We excluded children with severe neurologic impairments, congenital malformations, or chromosomal abnormalities. Neuropsychological assessments consisted of 5 neuropsychological tests and 3 questionnaires. Results: A total of 37 children (mean age, 9.1±1.2 years) participated. The mean gestational age at birth was 34.6±7.5 weeks, while the mean birth weight was 2,229.2±472.8 g. The mean full-scale intelligence quotient was 92.89±11.90; 24.3% scored between 70 and 85 (borderline intelligence functioning). An abnormal score was noted for at least one of the variables on the attention deficit hyperactivity disorder diagnostic system for 65% of the children. Scores below borderline function for executive quotient and memory quotient were 32.4% and 24.3%, respectively. Borderline or clinically relevant internalizing problems were noted in 13.5% on the Child Behavior Check List. There were no significant associations between perinatal factors or socioeconomic status and cognitive, visual perception, executive function, or behavior outcomes. Conclusion: Moderate to late preterm infants are at risk of developing borderline intelligence functioning and attention problems at early school age. Cognitive and executive functions that are important for academic performance must be carefully monitored and continuously followed up in moderate to late preterm infants.