• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.632-657
• /
• 2022

Detecting web attacks is a major challenge, and it is observed that the use of simple models leads to low sensitivity or high false positive problems. In this study, we aim to develop a robust two-stage deep learning based stacked ensemble web application firewall. Normal and abnormal classification is carried out in the first stage of the proposed WAF model. The classification process of the types of abnormal traffics is postponed to the second stage and carried out using an integrated stacked ensemble model. By this way, clients' requests can be served without time delay, and attack types can be detected with high sensitivity. In addition to the high accuracy of the proposed model, by using the statistical similarity and diversity analyses in the study, high generalization for the ensemble model is achieved. Within the study, a comprehensive, up-to-date, and robust multi-class web anomaly dataset named GAZI-HTTP is created in accordance with the real-world situations. The performance of the proposed WAF model is compared to state-of-the-art deep learning models and previous studies using the benchmark dataset. The proposed two-stage model achieved multi-class detection rates of 97.43% and 94.77% for GAZI-HTTP and ECML-PKDD, respectively.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.1
• /
• pp.59-74
• /
• 2020

The web space where web applications run is the cyber information warfare of attackers and defenders due to the open HTML. In the cyber attack space, about 84% of worldwide attacks exploit vulnerabilities in web applications and software. It is very difficult to detect web vulnerability attacks with security products such as web firewalls, and high labor costs are required for security verification and assurance of web applications. Therefore, rapid vulnerability detection and response in web space by automated software is a key and effective cyber attack defense strategy. In this paper, we establish a security risk management model by intensively analyzing security threats against web applications and software, and propose a method to effectively diagnose web and application vulnerabilities. The testing results on the commercial service are analyzed to prove that our approach is more effective than the other existing methods.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.5
• /
• pp.1235-1241
• /
• 2016

Personalized App recommendation system is recently famous since the number of various apps that can be used in smart phones that increases exponentially. However, the site users using google play site with malwares have experienced severe damages of privacy exposure and extortion as well as a simple damage of satisfaction descent at the same time. In addition, Sybil attack (Sybil) manipulating the score (rating) of each app with falmay also present because of the social networks development. Up until now, the sybil detection studies and malicious apps studies have been conducted independently. But it is important to determine finally the existence of intelligent attack with Sybil and malware simultaneously when we consider the intelligent attack types in real-time. Therefore, in this paper we experimentally evaluate the relationship between malware and sybils based on real cralwed dataset of goodlplay. Through the extensive evaluations, the correlation between malware and sybils is low for malware providers to hide themselves from Anti-Virus (AV).

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.1
• /
• pp.125-132
• /
• 2011

A hierarchical Web Security System, which is a solution to various web-based attacks, seemingly is not able to keep up with the improvement of detoured or compound attacks. In this paper, we suggest an efficient detecting scheme for web-based attacks like Malware, XSS, Creating Webshell, URL Spoofing, and Exposing Private Information through monitoring HTTP outbound traffics in real time. Our proposed scheme detects web-based attacks by comparing the outbound traffics with the signatures of HTML tag or Javascript created by the attacks. Through the verification analysis under the real-attacked environment, we show that our scheme installed in a hierarchical web security system has superior detection capability for detoured web-based attacks.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.5
• /
• pp.1223-1234
• /
• 2016

The Industrial control system is adopted by various industry field and national infrastructure, therefore if it received cyber attack, the serious security problems can be occured in the public sector. For this reason, security requirements of the industrial control system have been proposed, in accordance with the security guidelines of the electronic control system, and it is operated by separate from the external and the internal network. Nevertheless, cyber attack by malware (such as Stuxnet) targeting to control system have been occurred continuously, and also the real-time detection of untrusted traffic is very difficult because there are some difficulty of keeping up with quickly evolving the advent of new-variant malicious codes. In this paper, we propose the traffic analysis architecture for providing secure industrial control system based on the analyzed the security threats, the security requirements, and our proposed architecture.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.19 no.1
• /
• pp.103-111
• /
• 2009

Recently, cyber attacks against public communications networks are getting more complicated and varied. Moreover, in some cases, one country could make systematic attacks at a national level against another country to steal its confidential information and intellectual property. Therefore, the issue of cyber attacks is now regarded as a new major threat to national security. The conventional way of operating individual information security systems such as IDS and IPS may not be sufficient to cope with those attacks committed by highly-motivated attackers with significant resources. As a result, the monitoring and control of cyber security, which enables attack detection, analysis and response on a real-time basis has become of paramount importance. This paper discusses how to improve efficiency and effectiveness of national cyber security monitoring and control services. It first reviews major threats to the public communications network and how the responses to these threats are made and then it proposes a new approach to improve the national cyber security monitoring and control services.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.24 no.3
• /
• pp.491-498
• /
• 2014

Recently, cyber terror has been occurred frequently based on advanced persistent threat(APT) and it is very difficult to detect these attacks because of new malwares which cannot be detected by anti-virus softwares. This paper proposes and verifies the algorithms to detect the advanced persistent threat previously through real-time network monitoring and combinatorial analysis of big data log. In the future, APT attacks can be detected more easily by enhancing these algorithms and adapting big data platform.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.166-169
• /
• 2018

캐시 부채널 공격 중 하나인 FLUSH+RELOAD 공격은 높은 해상도와 적은 오류로 그 위험성이 높고, 여러가지 프로그램에서도 적용되어 개인정보의 유출에 대한 위험성까지 증명 되었다. 따라서 이 공격을 막기 위해 실시간으로 감지 할 수 있어야 할 필요성이 있다. 본 연구에서는 4가지 실험을 통하여 이 FLUSH+RELOAD 공격을 받을 때 PCM(Performance Counter Monitor)를 사용해 각각의 counter들의 값의 변화를 관찰하여 3가지 중요한 요인에 의해 공격 탐지를 할 수 있다는 것을 발견하였다. 이를 이용하여 머신 러닝의 logistic regression과 ANN(Artificial Neural Network)를 사용해 결과에 대한 각각 학습을 시킨 뒤, 실시간으로 공격에 대한 탐지를 할 수 있는 프로그램을 제작하였다. 일정한 시간동안 공격을 진행하여 모든 공격을 감지하는데 성공하였고, 상대적으로 적은 오탐률을 보여주었다.

• The KIPS Transactions:PartC
• /
• v.10C no.6
• /
• pp.675-682
• /
• 2003

Attackers collect vulnerabilities of a target computer system to intrude into it. And using several attack methods, they acquire root privilege. They steal and alter information in the computer system, or destroy the computer sysem. So far many intrusion detection systems and firewallshave been developed, but recently attackers go round these systems and intrude into a computer system . In this paper, we propose security kernel module to prevent attackers having acquired root privilege from doing illegal behaviors. It enhances administrator authentication with additional password, so prevents attackers from doing illegal behaviors such as modification of important files and installation of rootkits. It sends warning mail about sttacker's illegal behaviors to administrators by real time. So using information in the mail, they can estabilish new security policies.

• Journal of Information Technology Services
• /
• v.22 no.5
• /
• pp.99-108
• /
• 2023

As the computerization of hospitals becomes more advanced, security issues regarding data generated from various medical devices within hospitals are gradually increasing. For example, because hospital data contains a variety of personal information, attempts to attack it have been continuously made. In order to safely protect data from external attacks, each hospital has formed an internal team to continuously monitor whether the computer network is safely protected. However, there are limits to how humans can monitor attacks that occur on networks within hospitals in real time. Recently, artificial intelligence models have shown excellent performance in detecting outliers. In this paper, an experiment was conducted to verify how well an artificial intelligence model classifies normal and abnormal data in network traffic data generated from medical devices. There are several models used for outlier detection, but among them, Random Forest and Tabnet were used. Tabnet is a deep learning algorithm related to receive and classify structured data. Two algorithms were trained using open traffic network data, and the classification accuracy of the model was measured using test data. As a result, the random forest algorithm showed a classification accuracy of 93%, and Tapnet showed a classification accuracy of 99%. Therefore, it is expected that most outliers that may occur in a hospital network can be detected using an excellent algorithm such as Tabnet.