• The Journal of the Korea Contents Association
• /
• v.16 no.11
• /
• pp.139-153
• /
• 2016

Cyber incident collected from cyber-threat-intelligence sharing Center is growing rapidly due to expanding malicious code. It is difficult for Incident analysts to extract and classify similar features due to Cyber Attacks. To solve these problems the existing Similarity Analysis Method is based on single or multiple cyber observable of similar incidents from Cyber Attacks data mining. This method reduce the workload for the analysis but still has a problem with enhancing the unreality caused by the provision of improper and ambiguous information. We propose a incident analysis model performed similarity analysis on the hierarchically classified cyber observable based on cyber incident that can enhance both availability by the provision of proper information. Appling specific cyber incident analysis model, we will develop a system which will actually perform and verify our suggested model.

• The Journal of the Korea Contents Association
• /
• v.17 no.3
• /
• pp.231-237
• /
• 2017

Threat intelligences collected from cyber incident sharing system and security events collected from Security Information & Event Management system are analyzed and coped with expanding malicious code rapidly with the advent of big data. Analytical classification of the threat intelligence in cyber incidents requires various features of cyber observable. Therefore it is necessary to improve classification accuracy of the similarity by using multi-profile which is classified as the same features of cyber observables. We propose a multi-profile ensemble model performed similarity analysis on cyber incident of threat intelligence based on both attack types and cyber observables that can enhance the accuracy of the classification. We see a potential improvement of the cyber incident analysis system, which enhance the accuracy of the classification. Implementation of our suggested technique in a computer network offers the ability to classify and detect similar cyber incident of those not detected by other mechanisms.

• Korean Journal of Social Welfare Studies
• /
• v.44 no.3
• /
• pp.5-30
• /
• 2013

The aim of this study is to identify the influence of public housing on depression of its residents by analyzing the 7th Korea welfare panel study. To reduce the selection bias which arise from the public housing is selected by personal choice, we used PSM(propensity score matching). In addition, we merged the result of PSM and OLS regression to control the other variables which can affect depression of the resident of public housing. Final result revealed that the statistical significance which was observed when we compared the level of depression between the residents of public housing and general community by independent t-test was not observed when we used the merged result from PSM and regression. These results suggest that the high level of depression in the residents of public housing might be related with their demographic characteristics or earned income not with the public housing itself. This study can be the evidence supporting the policy of providing public housing because living in public housing did not give negative influence on its residents. Considering that this study also showed that there were no observable positive influences of public housing, we can suggest that public housing policy for majority of people not limited to people with low income.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.3
• /
• pp.1100-1118
• /
• 2021

In a wide range of ML applications, the training data contains privacy-sensitive information that should be kept secure. Training the ML systems by privacy-sensitive data makes the ML model inherent to the data. As the structure of the model has been fine-tuned by training data, the model can be abused for accessing the data by the estimation in a reverse process called model inversion attack (MIA). Although, MIA has been applied to shallow neural network models of recognizers in literature and its threat in privacy violation has been approved, in the case of a deep learning (DL) model, its efficiency was under question. It was due to the complexity of a DL model structure, big number of DL model parameters, the huge size of training data, big number of registered users to a DL model and thereof big number of class labels. This research work first analyses the possibility of MIA on a deep learning model of a recognition system, namely a face recognizer. Second, despite the conventional MIA under the white box scenario of having partial access to the users' non-sensitive information in addition to the model structure, the MIA is implemented on a deep face recognition system by just having the model structure and parameters but not any user information. In this aspect, it is under a semi-white box scenario or in other words a gray-box scenario. The experimental results in targeting five registered users of a CNN-based face recognition system approve the possibility of regeneration of users' face images even for a deep model by MIA under a gray box scenario. Although, for some images the evaluation recognition score is low and the generated images are not easily recognizable, but for some other images the score is high and facial features of the targeted identities are observable. The objective and subjective evaluations demonstrate that privacy cyber-attack by MIA on a deep recognition system not only is feasible but also is a serious threat with increasing alert state in the future as there is considerable potential for integration more advanced ML techniques to MIA.