Search

Cyber-security systems collect information from multiple security sensors to detect network intrusions and their models. As attacks become more complex and security systems diversify, the data used by intrusion-detection systems becomes more dimensional and large-scale. Intrusion detection based on intelligent anomaly detection detects attacks based on machine-learning classification models, soft computing, and rule sets. Feature-selection methods are used for efficient intrusion detection and solving high-dimensional problems. Optimized feature selection can maximize the detection model performance; thus, a fitness function design is required. We proposed an optimization algorithm-based feature-selection algorithm to improve anomaly-detection performance. We used a genetic algorithm and proposed an advanced fitness function that finds the most relevant feature set, increasing the detection rate, reducing the error rate, and enhancing analysis speed. An improved fitness function for the selection of optimized features is proposed; this function can address overfitting by solving the problem of anomaly-detection performance from imbalanced security datasets. The proposed algorithm outperformed other feature-selection algorithms. It outperformed the PCA and wrapper-DR methods, with 0.99564 at 10%, 0.996455 at 15%, and 0.996679 at 20%. It performed higher than wrapper-DR by 0.95% and PCA by 3.76%, showing higher differences in performance than in detection rates.

This study evaluated Staphylococcus aureus growth and subsequent staphylococcal enterotoxin A production in tryptone soy broth and on ready-to-eat cooked fish paste at 12 to 37 °C, as well as cross-contamination between stainless steel, polyethylene, and latex glove at room temperature. A model was developed using Barany and Roberts's growth model, which satisfactorily described the suitable growth of S. aureus with R(2)-adj from 0.94 to 0.99. Except at 12 °C, S. aureus cells in TSB presented a lag time lower (14.64 to 1.65 h), grew faster (0.08 to 0.31 log CFU/h) and produced SEA at lower cell density levels (5.65 to 6.44 log CFU/mL) compare to those inoculated on cooked fish paste with data of 16.920 to 1.985 h, 0.02 to 0.23 log CFU/h, and 6.19 to 7.11 log CFU/g, respectively. Staphylococcal enterotoxin type A (SEA) visual immunoassay test showed that primary SEA detection varied considerably among different storage temperature degrees and media. For example, it occurred only during exponential phase at 30 and 37 °C in TSB, but in cooked fish paste it took place at late exponential phase of S. aureus growth at 20 and 25 °C. The SEA detection test was negative on presence of S. aureus on cooked fish paste stored at 12 and 15 °C, although cell density reached level of 6.12 log CFU/g at 15 °C. Cross-contamination expressed as transfer rate of S. aureus from polyethylene surface to cooked fish paste surface was slower than that observed with steel surface to cooked fish paste under same conditions. These results provide helpful information for controlling S. aureus growth, SEA production and cross-contamination during processing of cooked fish paste.

The aim of this study was to model the growth kinetics of Listeria monocytogenes on ready-to-eat ham and sausage at different temperatures (4 to 35°C). The observed data fitted well with four primary models (Baranyi, modified Gompertz, logistic, and Huang) with high coefficients of determination (R(2) > 0.98) at all measured temperatures. After the mean square error (0.009 to 0.051), bias factors (0.99 to1.06), and accuracy factors (1.01 to 1.09) were obtained in all models, the square root and the natural logarithm model were employed to describe the relation between temperature and specific growth rate (SGR) and lag time (LT) derived from the primary models. These models were validated against the independent data observed from additional experiments using the acceptable prediction zone method and the proportion of the standard error of prediction. All secondary models based on each of the four primary models were acceptable to describe the growth of the pathogen in the two samples. The validation results indicate that the optimal primary model for estimating the SGR was the Baranyi model, and the optimal primary model for estimating LT was the logistic model in ready-to-eat (RTE) ham. The Baranyi model was also the optimal model to estimate the SGR and LT in RTE sausage. These results could be used to standardize predictive models, which are commonly used to identify critical control points in hazard analysis and critical control point systems or for the quantitative microbial risk assessment to improve the food safety of RTE meat products.

Spam mail is one of the most general mail dysfunctions, which may cause psychological damage to internet users. As internet usage increases, the amount of spam mail has also gradually increased. Indiscriminate sending, in particular, occurs when spam mail is sent using smart phones or tablets connected to wireless networks. Spam mail consists of approximately 68% of mail traffic; however, it is believed that the true percentage of spam mail is at a much more severe level. In order to analyze and detect spammail, we introduce a technique based on spam mail characteristics and text mining; in particular, spam mail is detected by extracting the linguistic analysis and language processing. Existing spam mail is analyzed, and hidden spam signatures are extracted using text clustering. Our proposed method utilizes a text mining system to improve the detection and error detection rates for existing spam mail and to respond to new spam mail types.

Big Data is data of big size which is not processed, collected, stored, searched, analyzed by the existing database management system. The parallel genetic algorithm using the Hadoop for BigData technology is easily realized by implementing GA(Genetic Algorithm) using MapReduce in the Hadoop Distribution System. The previous study that the genetic algorithm using MapReduce is proposed suitable transforming for the GA by MapReduce. However, they did not show good performance because of frequently occurring data input and output. In this paper, we proposed the MRPGA(MapReduce Parallel Genetic Algorithm) using improvement Map and Reduce process and the parallel processing characteristic of MapReduce. The optimal solution can be found by using the topology, migration of parallel genetic algorithm and local search algorithm. The convergence speed of the proposal method is 1.5 times faster than that of the existing MapReduce SGA, and is the optimal solution can be found quickly by the number of sub-generation iteration. In addition, the MRPGA is able to improve the processing and analysis performance of Big Data technology.

As the firewall is a typical network security equipment, it is usually installed at most of internal/external networks and makes many packet data in/out. So analyzing the its logs stored in it can provide important and fundamental data on the network security research. However, along with development of c ommunications technology, the speed of internet network is improved and then the amount of log data is becoming 'Massive D ata' or 'BigData'. In this trend, there are limits to analyze log data using the traditional database model RDBMS. In this pa per, through our Method of Analyzing Firewall log data using MapReduce based on NoSQL, we have discovered that the introduci ng NoSQL data base model can more effectively analyze the massive log data than the traditional one. We have demonstr ated execellent performance of the NoSQL by comparing the performance of data processing with existing RDBMS. Also the pr oposed method is evaluated by experiments that detect the three attack patterns and shown that it is highly effective.Keywords: NoSQL, Firewall, Log Analysis, MapReduce, BigData 접수일(2013년 3월 29일), 수정일(1차: 2013년 6월 13일, 2차: 2013년 7월 1일), 게재확정일(2013년 7월 1일)* "이 논문은 2013년도 가천대학교 교내연구비 지원에 의한 결과임."(GCU-2013-R193)†주저자, cbm0728@gmail.com‡교신저자, mmhan@gachon.ac.kr (Corresponding author)

The Selective Encryption method encrypts the important and requisite parts of data. Since the method does not encrypt the whole of data, the amount of computation is small,which makes it faster and the resources can be used efficiently. The existing selective algorithms have vulnerabilities to the plain text attack and the image restoration attack using the motion vector. They are also vulnerable to the attack in storing and transmitting of the random table data using in encrypt and scramble. In this paper, we propose the selective encryption algorithm of motion vector based on S-Box to remove the vulnerabilities of the existing selective algorithms. The motion vectors generated by the end of motion estimation function of video encoding/decoding xored with S-Box table, are replaced to certain location by using mapping table. The S-Box and mapping table are generated by the secret key through the Rivest Cipher 4 (RC4) encryption algorithm. The proposed algorithm enhances the resistance against attacks through the reinforcement of video security, and thus, reduces the vulnerabilities of the existing algorithms such as I-Frame selective encryption and MVEA. Even though the level of security of the proposed algorithm is higher than the bit scrambling algorithms, it has much better security and higher processing rate than others selective algorithms.

The Weapon Target Allocation(WTA) problem is the NP-Complete problem. The WTA problem is that the threatful air targets are assigned by weapon of allies for killing the targets. A good solution of NP-complete problem is heuristic algorithms. Genetic algorithms are commonly used heuristic for global optimization, and it is good solution on the diverse problem domain. But there has been very little research done on the generation of their initial population. The initialization of population is one of the GA step, and it decide to initial value of individuals. In this paper, we propose to the population initialization method to improve a Genetic Algorithm. When it initializes population, the proposed algorithm reflects the characteristics of the WTA problem domain, and inherits the dominant gene. In addition, the search space widely spread in the problem space to find efficiently the good quality solution. In this paper, the proposed algorithm to verify performance examine that an analysis of various properties and the experimental results by analyzing the performance compare to other algorithms. The proposed algorithm compared to the other initialization methods and a general genetic algorithm. As a result, the proposed algorithm showed better performance in WTA problem than the other algorithms. In particular, the proposed algorithm is a good way to apply to the variety of situation WTA problem domain, because the proposed algorithm can be applied flexibly to WTA problem by the adjustment of RMI.

Data pre-processing, a step performed prior to data processing, converts data into a form that is easy to analyse. In this study, we propose a method for the pre-processing and integration of data collected from various sources to detect insider information leakage; further, we evaluate the performance of data pre-processing by performing classification and detection experiments with collected normal and abnormal log data. An insider information leakage attack scenario was created, and the attack data for this scenario were generated in order to collect the corresponding log data. This preprocessing stage improved the efficiency of information leakage analysis and detection, as demonstrated by the results of our experiments that shown the performance with accuracies of 0.9991 and 0.9997, respectively, in source classification. In addition, we found that securing the attack scenario and actual attack data is a very important factor in insider information leakage detection owing to the small amount of attack data.

This study was conducted to develop a predictive model to estimate the growth of Listeria monocytogenes on fresh pork during storage at constant temperatures (5, 10, 15, 20, 25, 30, and 35°C). The Baranyi model was fitted to growth data (log CFU per gram) to calculate the specific growth rate (SGR) and lag time (LT) with a high coefficient of determination (R(2)0.98). As expected, SGR increased with a decline in LT with rising temperatures in all samples. Secondary models were then developed to describe the variation of SGR and LT as a function of temperature. Subsequently, the developed models were validated with additional independent growth data collected at 7, 17, 27, and 37°C and from published reports using proportion of relative errors and proportion of standard error of prediction. The proportion of relative errors of the SGR and LT models developed herein were 0.79 and 0.18, respectively. In addition, the standard error of prediction values of the SGR and LT of L. monocytogenes ranged from 25.7 to 33.1% and from 44.92 to 58.44%, respectively. These results suggest that the model developed in this study was capable of predicting the growth of L. monocytogenes under various isothermal conditions.

This study evaluated Staphylococcus aureus growth and subsequent staphylococcal enterotoxin A production in tryptone soy broth and on ready-to-eat cooked fish paste at 12 to 37 °C, as well as cross-contamination between stainless steel, polyethylene, and latex glove at room temperature. A model was developed using Barany and Roberts's growth model, which satisfactorily described the suitable growth of S. aureus with R(2)-adj from 0.94 to 0.99. Except at 12 °C, S. aureus cells in TSB presented a lag time lower (14.64 to 1.65 h), grew faster (0.08 to 0.31 log CFU/h) and produced SEA at lower cell density levels (5.65 to 6.44 log CFU/mL) compare to those inoculated on cooked fish paste with data of 16.920 to 1.985 h, 0.02 to 0.23 log CFU/h, and 6.19 to 7.11 log CFU/g, respectively. Staphylococcal enterotoxin type A (SEA) visual immunoassay test showed that primary SEA detection varied considerably among different storage temperature degrees and media. For example, it occurred only during exponential phase at 30 and 37 °C in TSB, but in cooked fish paste it took place at late exponential phase of S. aureus growth at 20 and 25 °C. The SEA detection test was negative on presence of S. aureus on cooked fish paste stored at 12 and 15 °C, although cell density reached level of 6.12 log CFU/g at 15 °C. Cross-contamination expressed as transfer rate of S. aureus from polyethylene surface to cooked fish paste surface was slower than that observed with steel surface to cooked fish paste under same conditions. These results provide helpful information for controlling S. aureus growth, SEA production and cross-contamination during processing of cooked fish paste.

The problem of Weapon Target Allocation (WTA) is to find an optimum solution, the type of vector that our weapons assign to targets, to minimize the damage of our assets from the target of an enemy offending us. we proposed the novel parallel genetic algorithm for solved to the WTA problem. The proposed. As the first step, our proposed algorithm is to expand the problem search space through the Random Mutation Inherit (RMI) population initialization method thereby improving convergence performance. We proposed an algorithm which obtains the WTA solution quickly and solves the WTA problem efficiently.

With development of information technology, information system has been advanced in a battlefield situation, and it becomes key factors to obtain information about the enemy aircraft and analyze the situation in battlefield. Threat evaluation which is the key factor of analysis of a battlefield situation is a technology that evaluates threat values on the situation in accordance with air intelligence gotten through radar and provides information about weapon assignment. This stage requires the most accurate information than other stage in a battlefield situation. Most of data of threat evaluation is calculated by sensed sensor values and transmitted, but presentation of incorrect links of sensor data or data omission that could happen on the existing technique could cause confusion over decision making in a battlefield situation. Thus, the links must be defined accurately through knowledge of experts on various sensor data domain, and reliable threat consequences must be provided through adaptation and learning about unpredictable battlefields due to data omission. On this paper, a fusion system, a dynamic neuro fuzzy knowledge based inference system, which is favorable to adaptation and learning and presentation of expertise, is suggested and applied to threat evaluation.