• 전기전자학회논문지
• /
• 제23권4호
• /
• pp.1134-1139
• /
• 2019

One of the most important applications of computer vision algorithms is the detection of threat objects in x-ray security images. However, in the practical setting, this task is complicated by two properties inherent to the dataset, namely, the problem of class imbalance and visual complexity. In our previous work, we resolved the class imbalance problem by using a GAN-based anomaly detection to balance out the bias induced by training a classification model on a non-practical dataset. In this paper, we propose a new method to alleviate the visual complexity problem by using a KNN-based automatic cropping algorithm to remove distracting and irrelevant information from the x-ray images. We use the cropped images as inputs to our current model. Empirical results show substantial improvement to our model, e.g. about 3% in the practical dataset, thus further outperforming previous approaches, which is very critical for security-based applications.

• 정보보호학회논문지
• /
• 제29권2호
• /
• pp.439-449
• /
• 2019

ICBMA(IoT, Cloud, Big Data, Mobile, AI)로 대변되는 정보기술의 발전은 데이터의 급증과 이를 수용하기 위한 데이터센터의 수적, 양적 증가로 이어지고 있다. 이에 데이터센터를 사회 중요 기반시설로 인식하고, 테러 공격 대응 등 안전성 확보를 위해서는 사전에 물리보안 위협의 식별이 매우 중요하다. 본 논문에서는 위협의 식별과 분류를 쉽게 처리할 목적으로 물리보안 위협 분할도(PS-TBS)를 개발하고, 전문가 설문조사를 통하여 개발 된 물리보안 위협 분할도의 타당성과 효용성을 검증한다. 또한 위협 분할도의 항목에 대해 상세 정의를 통해 실무 활용을 통한 물리보안 수준 향상에 기여하고자 한다.

• 한국멀티미디어학회논문지
• /
• 제21권5호
• /
• pp.617-625
• /
• 2018

Phishing website has become a crucial concern in cyber security applications. It is performed by fraudulently deceiving users with the aim of obtaining their sensitive information such as bank account information, credit card, username, and password. The threat has led to huge losses to online retailers, e-business platform, financial institutions, and to name but a few. One way to build anti-phishing detection mechanism is to construct classification algorithm based on machine learning techniques. The objective of this paper is to compare different classifier ensemble approaches, i.e. random forest, rotation forest, gradient boosted machine, and extreme gradient boosting against single classifiers, i.e. decision tree, classification and regression tree, and credal decision tree in the case of website phishing. Area under ROC curve (AUC) is employed as a performance metric, whilst statistical tests are used as baseline indicator of significance evaluation among classifiers. The paper contributes the existing literature on making a benchmark of classifier ensembles for web phishing detection.

• Journal of Multimedia Information System
• /
• 제5권2호
• /
• pp.99-104
• /
• 2018

Phishing website has become a crucial concern in cyber security applications. It is performed by fraudulently deceiving users with the aim of obtaining their sensitive information such as bank account information, credit card, username, and password. The threat has led to huge losses to online retailers, e-business platform, financial institutions, and to name but a few. One way to build anti-phishing detection mechanism is to construct classification algorithm based on machine learning techniques. The objective of this paper is to compare different classifier ensemble approaches, i.e. random forest, rotation forest, gradient boosted machine, and extreme gradient boosting against single classifiers, i.e. decision tree, classification and regression tree, and credal decision tree in the case of website phishing. Area under ROC curve (AUC) is employed as a performance metric, whilst statistical tests are used as baseline indicator of significance evaluation among classifiers. The paper contributes the existing literature on making a benchmark of classifier ensembles for web phishing detection.

• International Journal of Internet, Broadcasting and Communication
• /
• 제15권1호
• /
• pp.23-32
• /
• 2023

Since NFTs can be used like certificates due to the nature of blockchain, their use in various digital asset trading markets is expanding. This is because NFTs are expected to be actively used as a core technology of the metaverse virtual economy as non-transferable NFTs are developed. However, concerns about NFT security threats are also growing. Therefore, the purpose of this study is to investigate and analyze NFT-related infringement cases and to clearly understand the current security status and risks. As a research method, we determined NFT security areas based on previous studies and analyzed infringement cases and threat types for each area. The analysis results were systematically mapped in the form of domain, case, and threat, and the meaning of the comprehensive results was presented. As a result of the research, we want to help researchers clearly understand the current state of NFT security and seek the right research direction.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2005년도 추계학술대회 논문집
• /
• pp.599-604
• /
• 2005

As a public transportation possible to convey a large quantity, the railway is safe and keeps time, but it has hazards to cause a disaster if the accidents such as collision, derailment, and fire occur. So advanced countries carry out System Safety Plan with various program activities which have connected orders to maintain or improve safety level by finding hazards, evaluation, taking measures and practice, and improving problems. Especially they systematically manage hazards to cause railway accidents and the factors which possibly threat safety, using national classification of risk and causes with analysis of the related data such as establishing accident/incident data and safety regulations/standards. As executing railway safety regulations, domestic railway is currently trying to improve railway safety management system. The research of classification system of accidents/incidents is one thing to make railway safety management systems better. In this research, we reviewed hazardous factors of railway systems and classification of the causes as the beginning of system safety management, and we conducted study on development of railway accident classification based on findings of this research. The results are able to be used in identifying hazards and activities of systemic safety management at the step of railway accident report and investigation.

• 융합보안논문지
• /
• 제7권1호
• /
• pp.19-27
• /
• 2007

알려지지 않은 불분명한 위협을 검출하는 내는 것은 모순이다. 존재하는 것이 알려지지 않았다면 어떻게 찾아 낼 것인가? 그것은 알려지지 알은 위험을 아주 짧은 시간 안에 위협을 정의(identification)을 할 수 있으면 가능 할 수 있을 것이다. 본 논문은 위험 검출 기법을 만들어 네트워크상의 알려지지 않은 위험에 대해 유연하게 대처할 수 있는 시스템 개발에 도움을 줄 수 있게 하기 위해 연구되었다. 이 시스템은 알려지지 않은 위험을 탐지하기 위하여 동적이고 유연한 상황 지식을 가진 로직을 가지고 시스템을 감시한다. 시스템은 새로운 위협의 검출뿐만 아니라 빠르고 효과적인 방법으로 위협에 대처할 수 있다.

• IEIE Transactions on Smart Processing and Computing
• /
• 제5권2호
• /
• pp.94-99
• /
• 2016

Application layer attacks have for years posed an ever-serious threat to network security, since they always come after a technically legitimate connection has been established. In recent years, cyber criminals have turned to fully exploiting the web as a medium of communication to launch a variety of forbidden or illicit activities by spreading malicious automated software (auto-ware) such as adware, spyware, or bots. When this malicious auto-ware infects a network, it will act like a robot, mimic normal behavior of web access, and bypass the network firewall or intrusion detection system. Besides that, in a private and large network, with huge Hypertext Transfer Protocol (HTTP) traffic generated each day, communication behavior identification and classification of auto-ware is a challenge. In this paper, based on a previous study, analysis of auto-ware communication behavior, and with the addition of new features, a method for classification of HTTP auto-ware communication is proposed. For that, a Not Only Structured Query Language (NoSQL) database is applied to handle large volumes of unstructured HTTP requests captured every day. The method is tested with real HTTP traffic data collected through a proxy server of a private network, providing good results in the classification and detection of suspicious auto-ware web access.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권8호
• /
• pp.4285-4299
• /
• 2019

Adversarial attack is a technique that causes a malfunction of classification models by adding noise that cannot be distinguished by humans, which poses a threat to a deep learning model. In this paper, we propose an efficient method to detect adversarial images using Gaussian process regression. Existing deep learning-based adversarial detection methods require numerous adversarial images for their training. The proposed method overcomes this problem by performing classification based on the statistical features of adversarial images and clean images that are extracted by Gaussian process regression with a small number of images. This technique can determine whether the input image is an adversarial image by applying Gaussian process regression based on the intermediate output value of the classification model. Experimental results show that the proposed method achieves higher detection performance than the other deep learning-based adversarial detection methods for powerful attacks. In particular, the Gaussian process regression-based detector shows better detection performance than the baseline models for most attacks in the case with fewer adversarial examples.

• 정보보호학회논문지
• /
• 제22권5호
• /
• pp.1191-1204
• /
• 2012

정보보안시스템을 무력화하는 공격이 나타남에 따라, 정보보안제품의 취약성을 분석하는 보안 테스팅에 대한 관심이 높아지고 있다. 보안제품 개발의 주요 단계인 침투 테스팅은, 공격자가 악용할 수 있는 취약성을 찾기 위해 컴퓨터 시스템을 실제적으로 테스팅하는 것이다. 침투 테스팅과 같은 보안 테스팅은 대상 시스템에 대한 정보 수집, 가능한 진입점 식별, 침입 시도, 결과 보고 등의 과정을 포함한다. 따라서 취약성 분석 및 보안 테스팅에서 일반성, 재사용성, 효율성을 극대화하는 것이 매우 중요하다. 본 논문에서는, 정보보호제품이 자신의 보안 기능을 무력화하거나 우회하는 공격에 대응할 수 있는 자체보호기능 및 우회불가성을 제공하는 가를 평가할 수 있는 위협분석 기반의 소프트웨어 보안 테스팅을 제안한다. 위협분석으로 취약성을 식별한 후, 보안 테스팅의 재사용성과 효율성을 개선하기 위해 소프트웨어 모듈과 보안 기능에 따라 테스팅 전략을 수립한다. 제안기법은 위협 분석 및 테스팅 분류, 적절한 보안테스팅 전략 선정, 보안 테스팅으로 구성된다. 사례연구와 보안테스팅을 통해 제안 기법이 보안 시스템을 체계적으로 평가할 수 있음을 보였다.