• Proceedings of the KAIS Fall Conference
• /
• 2012.05b
• /
• pp.835-838
• /
• 2012

최근 스마트폰의 폭팔적인 증가와 함께 사용 환경개선도 이루어 지고 있다. 또한 Wi-Fi 존의 증가와 LTE같은 빠른 네트워크 환경은 사용자 중심의 수 많은 앱을 탄생시키고 있다. 안드로이드는 애플의 iOS와는 다른 오픈소스 정책으로 플랫폼 소스가 공개되어 있어 많은 개발자가 쉽게 접근이 가능하다. 그러나 안드로이드는 앱(App) 검증 체계가 미흡하기 때문에 악성코드 등으로 인한 위협요소가 존재하고 있다. 또한 파일 시스템은 임의적 접근제어방식으로 공격자가 취약점을 통해 관리자 권한을 얻어 시스템 자원을 제어할 수 있기 때문에 위협요소가 다분하다. 본 논문에서는 스마트폰 앱이 호출하는 시스템 API 및 네트워크 자원사용 패턴을 분석하여 부정 앱을 차단하는 방법을 제안하였다. 제안 방법으로 실험한 결과 API호출 빈도 및 자원 사용률이 최소 기준치 이하로 검출된 경우를 제외한 평가대상은 모두 검출하여 보안성 강화에 효과적인 것으로 실험을 통하여 검증하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2017.01a
• /
• pp.219-222
• /
• 2017

드론 기술이 발전하면서 물품 배달에 드론이 이용되는 등 드론은 우리 생활 전반에 자리 잡으려 하고 있다. 하지만 대부분의 드론이 기본적인 사용자 인증 과정도 없이 보안에 매우 취약한 상태이다. 본 논문에서는 드론의 취약점을 증명하기 위해 Parrot사의 AR. Drone을 대상으로 Wi-Fi 연결을 통한 인증해제, telnet을 통한 명령 수행, ftp 서버를 통한 파일 변조 공격을 적용해 보고, 이러한 취약점에 대해 무선 AP의 비밀번호를 복잡하게 설정하는 방법, 무선 침입 방지 시스템을 사용하는 방법, NAP 또는 NAC 솔루션을 구축하는 방법과 같은 적절한 대응 방안을 논의한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.01a
• /
• pp.143-146
• /
• 2018

서명기반 악성코드 탐지는 악성 파일의 고유 해싱 값을 사용하거나 패턴화된 공격 규칙을 이용하므로, 변형된 악성코드 탐지에 취약한 단점이 있다. 기계 학습을 적용한 악성코드 탐지는 이러한 취약점을 극복할 수 있는 방안으로 인식되고 있다. 본 논문은 정적 분석으로 n-gram과 API 특징점을 추출해 특징 벡터로 구성하여 XGBoost, k-최근접 이웃 알고리즘, 지지 벡터 기기, 신경망 알고리즘, 심층 학습 알고리즘의 일반화 성능을 비교한다. 실험 결과로 XGBoost가 일반화 성능이 99%로 가장 우수했으며 k-최근접 이웃 알고리즘이 학습 시간이 가장 적게 소요됐다. 일반화 성능과 시간 복잡도 측면에서 XGBoost가 비교 대상 알고리즘에 비해 우수한 성능을 보였다.

• Review of KIISC
• /
• v.31 no.6
• /
• pp.5-12
• /
• 2021

랜섬웨어는 2021년 가장 주목해야 할 사이버 위협으로 여겨지며, 전 세계적으로 큰 피해를 입혔다. 특히 국가 핵심 인프라 시설과 기업을 대상으로 대규모 공격을 지속하였으며, 파일을 암호화하는 것 뿐만 아니라 기업의 기밀 정보를 유출함으로써 2차 피해 우려를 낳고 있다. 이에 따라 세계 각국에서는 랜섬웨어를 대응 및 예방하고자 다양한 지침을 발표하였다. 본 논문에서는 2021년 국내·외에서 발생한 랜섬웨어 사건·사고와 새롭게 등장한 랜섬웨어에 대해 알아보고, 국가별 랜섬웨어 대응 및 예방 정책에 관해 소개한다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.4
• /
• pp.775-784
• /
• 2019

Malware infringement attacks are continuously increasing in various environments such as mobile, IOT, windows and mac due to the emergence of new and variant malware, and signature-based countermeasures have limitations in detection of malware. In addition, analytical performance is deteriorating due to obfuscation, packing, and anti-VM technique. In this paper, we propose a system that can detect malware based on machine learning by using similarity hashing-based pattern detection technique and static analysis after file classification according to packing. This enables more efficient detection because it utilizes both pattern-based detection, which is well-known malware detection, and machine learning-based detection technology, which is advantageous for detecting new and variant malware. The results of this study were obtained by detecting accuracy of 95.79% or more for benign sample files and malware sample files provided by the AI-based malware detection track of the Information Security R&D Data Challenge 2018 competition. In the future, it is expected that it will be possible to build a system that improves detection performance by applying a feature vector and a detection method to the characteristics of a packed file.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.21 no.1
• /
• pp.125-133
• /
• 2011

According to proliferation of mobile devices, security threats have been continuously increased such as illegal or unintentional file transmission of important data to an external mass-storage device. Therefore, we propose a protection method to prohibit an illegal outflow to this device and implement this method. This method extracts signatures from random locations of important file and uses them to detect and block illegal file transmission. To get signatures, a target file is divided by extracting window size and more than one signatures are extracted in this area. To effective signature sampling, various extraction ways such as full, binomial distribution-based and dynamic sampling are implemented and evaluated. The proposed method has some advantages. The one is that an attacker cannot easily predict the signature and its extraction location. The other is that it doesn't need to modify original data to protect it. With the help of these advantages, we can say that this method can increase efficiency of easy-to-use and it is a proper way leakage prevention in a mobile device.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.12
• /
• pp.480-490
• /
• 2018

This study investigated the profiles of anger expression (anger control, anger in, anger out) and their variation in forms, and determined the differences in depression, aggression, and negative affect intensity of middle school students. For this purpose, the survey responses of 296 middle school students in Seoul were analyzed. The major study results are as follows. (1) Cluster analyses yielded four anger expression profiles: cluster 1 was characterized by high scores for anger control, anger in and anger out, cluster 2 by low scores for anger control, high scores for anger in and anger out, cluster 3 by low scores for anger control, anger in and anger out, and cluster 4 by low scores for anger in, high scores for anger control and anger out. (2) Between-cluster differences in depression, aggression, and negative affect intensity were all significant. The posteriori test indicated that cluster 4 was higher than the other three clusters in terms of depression. Cluster 3 was higher than the other three clusters on aggression, cluster 2 was higher than cluster 4 in terms of aggression. The interventions by aggression expression cluster are discussed and the implications of this research to education and counseling are explained.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.4
• /
• pp.859-866
• /
• 2019

Cybersecurity attack targeting a specific user is rising in number, even enterprises are trying to strengthen their cybersecurity. Network segmentation environment where public network and private network are separated could block information coming from the outside, however, it is unable to control outside information for business efficiency and productivity. Even if enterprises try to enhance security policies and introduce the network segmentation system and a solution incorporating CDR technology to remove unnecessary data contained in files, it is still exposed to security threats. Therefore, we suggest a system that uses file format conversion to transmit a secure file in the network separation environment. The secure file is converted into an image file from a document, as it reflects attack patterns of inserting malicious code into the document file. Additionally, this paper proposes a system in the environment which functions that a document file can keep information for incident response, considering forensic readiness.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.3
• /
• pp.563-577
• /
• 2017

Due to the Internet and computing capability, new and variant malware are discovered around 1 Million per day. Companies use dynamic analysis such as behavior analysis on virtual machines for unknown malware detection because attackers use unknown malware which is not detected by signature based AV effectively. But growing number of malware types are not only PE(Portable Executable) but also non-PE such as MS word or PDF therefore dynamic analysis must need more resources and computing powers to improve detection effectiveness. This study elicits the pre-filtering system evaluation factor to improve effective dynamic malware analysis system and presents and verifies the decision making model and the formula for solution selection using AHP(Analytics Hierarchy Process)

• Journal of Internet Computing and Services
• /
• v.19 no.5
• /
• pp.21-31
• /
• 2018

Cyber penetration attacks can not only damage cyber space but can attack entire infrastructure such as electricity, gas, water, and nuclear power, which can cause enormous damage to the lives of the people. Also, cyber space has already been defined as the fifth battlefield, and strategic responses are very important. Most of recent cyber attacks are caused by malicious code, and since the number is more than 1.6 million per day, automated analysis technology to cope with a large amount of malicious code is very important. However, it is difficult to deal with malicious code encryption, obfuscation and packing, and the dynamic analysis technique is not limited to the performance requirements of dynamic analysis but also to the virtual There is a limit in coping with environment avoiding technology. In this paper, we propose a machine learning based malicious code analysis technique which improve the weakness of the detection performance of existing analysis technology while maintaining the light and high-speed analysis performance applicable to commercial endpoints. The results of this study show that 99.13% accuracy, 99.26% precision and 99.09% recall analysis performance of 71,000 normal file and malicious code in commercial environment and analysis time in PC environment can be analyzed more than 5 per second, and it can be operated independently in the endpoint environment and it is considered that it works in complementary form in operation in conjunction with existing antivirus technology and static and dynamic analysis technology. It is also expected to be used as a core element of EDR technology and malware variant analysis.