http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
머신러닝을 활용한 행위 및 스크립트 유사도 기반 크립토재킹 탐지 프레임워크
임은지(EunJi Lim),이은영(EunYoung Lee),이일구(IlGu Lee) 한국정보보호학회 2021 정보보호학회논문지 Vol.31 No.6
최근 급상승한 암호 화폐의 인기로 인해 암호 화폐 채굴 악성코드인 크립토재킹 위협이 증가하고 있다. 특히 웹기반 크립토재킹은 피해자가 웹 사이트에 접속만 하여도 피해자의 PC 자원을 사용해 암호 화폐를 채굴할 수 있으며 간단하게 채굴 스크립트만 추가하면 되기 때문에 공격이 쉽고 성능 열화와 고장의 원인이 된다. 크립토재킹은 피해자가 피해 상황을 인지하기 어렵기 때문에 크립토재킹을 효율적으로 탐지하고 차단할 수 있는 연구가 필요하다. 본 연구에서는 크립토재킹의 대표적인 감염 증상과 스크립트를 지표로 활용하여 효과적으로 크립토재킹을 탐지하는 프레임워크를 제안하고 평가한다. 제안한 크립토재킹 탐지 프레임워크에서 행위 기반 동적 분석 기법으로 컴퓨터 성능지표를 학습한 K-Nearest Neighbors(KNN) 모델을 활용했고, 스크립트 유사도 기반 정적 분석 기법은 악성 스크립트 단어 빈도수를 학습한 K-means 모델을 크립토재킹 탐지에 활용했다. 실험 결과에 따르면 KNN 모델은 99.6%의 정확도를 보였고, K-means 모델은 정상 군집의 실루엣 계수가 0.61인 것을 확인하였다. Due to the recent surge in popularity of cryptocurrency, the threat of cryptojacking, a malicious code for mining cryptocurrencies, is increasing. In particular, web-based cryptojacking is easy to attack because the victim can mine cryptocurrencies using the victim"s PC resources just by accessing the website and simply adding mining scripts. The cryptojacking attack causes poor performance and malfunction. It can also cause hardware failure due to overheating and aging caused by mining. Cryptojacking is difficult for victims to recognize the damage, so research is needed to efficiently detect and block cryptojacking. In this work, we take representative distinct symptoms of cryptojacking as an indicator and propose a new architecture. We utilized the K-Nearst Neighbors(KNN) model, which trained computer performance indicators as behavior-based dynamic analysis techniques. In addition, a K-means model, which trained the frequency of malicious script words for script similarity-based static analysis techniques, was utilized. The KNN model had 99.6% accuracy, and the K-means model had a silhouette coefficient of 0.61 for normal clusters.
임은지(Eunji Lim),김봉조(Bong-Jo Kim),이철순(Cheol-Soon Lee),차보석(Boseok Cha),이소진(So-Jin Lee),서지영(Jiyeong Seo),최재원(Jae-Won Choi),이영지(Young-Ji Lee),이윤정(Younjung Lee),이동윤(Dongyun Lee) 대한노인정신의학회 2021 노인정신의학 Vol.25 No.1
Objective: To investigate perceptions of coronavirus disease-19 (COVID-19) associated with anxiety caused by the COVID-19 epidemic in the elderly who are vulnerable to mental health problems. Methods: This study used data of a survey on perceptions of COVID-19 and changes in mental health of 1,000 out of residents in a province of Korea in April 2020. The survey included questions about psychological perceptions for COVID-19. Subjects were dived into two groups (<60 and ≥60). Binary logistic regression analyses were performed for evaluating the association between anxiety and perceptions about COVID-19 in each group. Results: Results of binary logistic regression analyses revealed that only ‘fear of getting infected myself’among perceptions for COVID-19 was associated with anxiety in the elderly aged more than 60 years. However, in adults aged less than 60 years, all perceptions for COVID-19 except impairment of performance were associated with such anxiety. Conclusion: We found that the anxiety for COVID-19 in elderly with age over 60 years was associated with ‘fear of getting infected myself’ rather than ‘fear of family or people around them’, unlike adults aged less than 60 years. These results can be applied in strategies for psychological quarantine against COVID-19 among the elderly.