• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.24 no.4
• /
• pp.617-624
• /
• 2014

Smart phone usage has increased exponentially and open source based Android OS occupy significant market share. However, various malicious applications that use the characteristic of Android threaten users. In this paper, we construct an efficient malicious application detector by using the principle component analysis and the incremental k nearest neighbor algorithm, which consider an required permission, of Android applications. The cross validation is exploited in order to find a critical parameter of the algorithm. For the performance evaluation of our approach, we simulate a real data set of Contagio Mobile.

• Journal of Convergence for Information Technology
• /
• v.11 no.5
• /
• pp.30-37
• /
• 2021

Various devices are connected to the Internet, and attacks using the Internet are occurring. Among such attacks, there are attacks that use malicious URLs to make users access to wrong phishing sites or distribute malicious viruses. Therefore, how to detect such malicious URL attacks is one of the important security issues. Among recent deep learning technologies, neural networks are showing good performance in image recognition, speech recognition, and pattern recognition. This neural network can be applied to research that analyzes and detects patterns of malicious URL characteristics. In this paper, performance analysis according to various parameters was performed on a method of detecting malicious URLs using neural networks. In this paper, malicious URL detection performance was analyzed while changing the activation function, learning rate, and neural network structure. The experimental data was crawled by Alexa top 1 million and Whois to build the data, and the machine learning library used TensorFlow. As a result of the experiment, when the number of layers is 4, the learning rate is 0.005, and the number of nodes in each layer is 100, the accuracy of 97.8% and the f1 score of 92.94% are obtained.

• Journal of KIISE
• /
• v.44 no.11
• /
• pp.1125-1129
• /
• 2017

LSTM(Long Short-term Memory) is a kind of RNN(Recurrent Neural Network) in which a next-state is updated by remembering the previous states. The information of calling a sequence in a malware can be defined as system call function that is called at each time. In this paper, we use calling sequences of system calls in malware codes as input for malware classification to utilize the feature remembering previous states via LSTM. We run an experiment to show that our method can classify malware and measure accuracy by changing the length of system call sequences.

• Journal of Korea Multimedia Society
• /
• v.13 no.5
• /
• pp.754-762
• /
• 2010

Nowadays, email-based targeted attacks using malcode-bearing documents have been steadily increased. To improve the success rate of the attack and avoid anti-viruses, attackers mainly employ zero-day exploits and relevant social engineering techniques. In this paper, we propose an architecture of the email vaccine cloud system to prevent targeted attacks using malcode-bearing documents. The system extracts attached document files from email messages, performs behavior analysis as well as signature-based detection in the virtual machine environment, and completely removes malicious documents from the messages. In the process of behavior analysis, the documents are regarded as malicious ones in cases of creating executable files, launching new processes, accessing critical registry entries, connecting to the Internet. The email vaccine cloud system will help prevent various cyber terrors such as information leakages by preventing email based targeted attacks.

• The Journal of the Korean dental association
• /
• v.27 no.8 s.243
• /
• pp.697-702
• /
• 1989

악성종양은 상피성의 암종(carcinoma)과 결체직성의 육종(sarcoma)으로 분류된다. 최근 암환자의 발생은 점차 증가되는 추세이며, 우리나라에서도 사망원인 중 뇌졸증 다음으로 암이 차지하는 비율이 높다. 이러한 암은 침윤성(infiltrative)인 성장으로 인하여 인접 정상조직을 급격히 파괴시키며, 해당 임파절을 따라 신체 다른 부위로 전이(metastasis)된다. 임파절에 전이되기 전에 조기발견된 암은 70%의 5년 생존률을 보이는 반면, 임파절에 전이된 후에 발견된 암은 30%의 5년 생존률을 보인다. 따라서 암의 성공적인 치료를 위해서는 이의 조기발견이 매우 중요하다고 할수 있다. 그러나 불행하게도 많은 환자가 이미 병소가 상당히 진행된 상태에서 내원하기 때문에 이의 근치가 어려우며, 예후 또한 좋지 않다. 이러한 암을 조기발견하기 위해서는 환자 자신의 관심뿐만 아니라 치과의사의 세심한 검진이 필요하리라 생각된다.

• Nuclear Medicine and Molecular Imaging
• /
• v.43 no.5
• /
• pp.402-410
• /
• 2009

Purpose: The aim of this study was to determine the incidence and malignant rate of incidental asymmetric palatine tonsillar uptake (ATU) on $^{18}F$-FDG PET/CT in various clinical indications and to evaluate the clinical and PET/CT findings suggesting malignancy. Materials and Methods: We retrospectively reviewed a total of 2,901 patients ($58.4{\pm}12.3$ yrs, range 20~88 yrs, M:F = 1,841:1,060) who underwent $^{18}F$-FDG PET/CT during an 1-year period with various indications except primary tonsillar cancer and lymphoma evaluation. On $^{18}F$-FDG PET/CT, metabolic abnormality of the palatine tonsil and cervical lymph node were visually assessed. ATU was defined as increased palatine tonsillar uptake with diffuse, focal, or irregular pattern compared to contralateral side. The incidence and malignant ratio of ATU were evaluated according to clinical and PET/CT findings. Results: Of 2,901 cases, 290(10,0%) showed ATU. The incidence of ATU showed seasonal variation and was high in the winter (12.1%). Of 209 cases with ATU confirmed pathologically and/or clinically, five (2.4%) were malignant lesions. ATU with irregular uptake pattern (2/2) and in cases referred for cervical lymph node metastasis of unknown origin (3/5) were frequently associated with malignant lesion (p<0.05). Conclusion: ATU was not infrequently observed on $^{18}F$-FDG PET/CT, and the malignant risk of ATU was low. However, ATU with cervical lymph node metastasis or with irregular pattern on PET/CT would be further evaluated by the histopathologic examination.

• Journal of Chest Surgery
• /
• v.37 no.3
• /
• pp.252-260
• /
• 2004

The purpose of study is to evaluate the clinical implication of malignant Pleural Lavage Cytology (PLC) in primary lung cancer. 315 patients were examined with pleural lavage cytology in Asan Medical Center between November 1998 and August 2002. The patients were chosen from primary lung cancer patients with no pleural effusion according to preoperative radiologic examination; no tumor invasion into the chest wall and no diffuse pleural adhesion in intraoperative findings, The pleural cavity and lung were washed with 100 $m\ell$ of warm normal saline. The 315 patients consisted of 237 men and 78 women. The incidence of malignant PLC was found in 28 patients (8.9%). For patients in early stages (I & II), survival rate was 93.9% in positive malignant PLC and 85.7% in negative malignant PLC. 31 patients (13.6%) had local or distant recurrences; 2-year recurrence-free rate was 90.1% in negative PLC and 87.5% in positive PLC. The survival and recurrence-free rate in each stage were not statistically associated with the result of PLC. Median follow-up was 16.4 months from the surgery. To access implication of malignant PLC in primary lung cancer, a long-term follow-up and further study are required.

• Korean Journal of Digital Imaging in Medicine
• /
• v.17 no.1
• /
• pp.19-31
• /
• 2015

최근 우리나라의 암 발생률은 꾸준히 증가추세에 있고 그 중에서도 전립선암은 갑상선암을 제외했을 때 남성에서 가장 높은 증가 추세를 보이고 있는 암이다. 전립선암은 그 동안 선진국에서 주로 발병하는 것으로 알려진 암 종이지만 서구화된 식습관과 생활 행태 변화로 인하여 국내에서도 발생률이 증가하는 것으로 추정하고 있다. 따라서 국내 환경에 맞는 내장 지방 분포와 같은 정확한 비만도 측정을 통해 우리나라에서 증가율 1위를 보이고 있는 전립선암 발생의 원인 관계를 찾고자 한다. 본 연구는 환자와 정상군 비교를 하는 환자-대조군 연구이고 본 연구를 위하여 임상시험 윤리위원회 (IRB) 승인을 받았다 (NCC2014-0124). 환자군은 2014년 8월 1일부터 2015년 1월 6일 까지 국립암센터를 방문하여 전립선암을 진단받고 수술과 항암치료 그리고 방사선 치료를 시작하지 않은 초진을 대상으로 하였고, 정상군은 2009년 11월부터 2014년 9월 30일까지 공단검진을 목적으로 국립암센터를 방문한 정상인을 대상으로 하였다. 전립선암 연구는 환자 총 52명에 평균 66세 (51 - 82세)이고 정상군은 총 50명에 평균 64세 (59 - 75세) 이다. 모든 연구 대상자들의 생활 요인 평가를 위하여 암 가족력, 흡연, 음주 상태, 운동, 등을 추가적으로 설문 조사하였다. MRI 영상의 배꼽 주위에서의 내장 지방과 피하지방을 전용 분석 컴퓨터를 활용하여 측정 하였다. 복부비만율은 환자군과 정상군에서뿐만 아니라 (p = 0.03), 전립선암 악성도와 (Gleasonscore; p = 0.001)도 통계적 차이를 나타냈다. 하지만 BMI 결과와는 전립선암 발생과 악성도에서 무관함을 보인 것에 반해 허리둘레는 전립선암의 발생에 영향을 미치는 결과를 나타났다. 한편 전립선암의 또 다른 악성도 지표인 PSA는 비만 측정치와의 상관성이 Gleason score와 보다 대체적으로 낮게 나타났다. 학력, 운동량, 흡연, 음주 상태와 같은 생활 특성에 따른 전립선암 발생의 영향 관계는 뚜렷하지 않았다. 결론적으로 본 연구를 통해서 전립선암의 발생 위험도와 악성도 지표로 복부 비만도가 유용함을 나타냈고 간단한 신체 계측 지표 활용으로는 BMI보다 허리둘레 측정치가 더 암 발생의 연관성이 높음을 보였다.

• Radiation Oncology Journal
• /
• v.23 no.2
• /
• pp.111-115
• /
• 2005

Primary malignant melanoma of the vagina is an extremely rare genital neoplasm occurring mainly on postmenopausal women. It has a worse prognosis than cutaneous melanomas, because of the high rate of loco-regional recurrences and rapid systemic dissemination. In the past, radical surgical extirpation as the primary management had been recommended to improve loco-regional control, and possibly overall survival. However, the prognosis was poor In spite of such a radical approache. Recently, more conservative treatment such as wide local excision combined with adjuvant high-dose fraction radiotherapy seems to have premising results. Primary radiation therapy could be served as an alternative to surgery for patients with lesion less than 3 cm in diameter. We report 2 cases of primary vaginal malignant melanoma treated with radiotherapy.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.4
• /
• pp.895-902
• /
• 2016

Smart phone distribution rate has been rising and it's security threat also has been rising. Especially Android smart phone reaches nearly 85% of domestic share. Since repackaging on android smart phone is relatively easy, the number of re-packaged malwares has shown steady increase. While many detection techniques have been proposed in order to prevent malwares, it is not easy to detect re-packaged malwares by static analysis and it is also difficult to operate dynamic analysis in android smart phone. Static analysis proposed in this paper features code reuse of repackaged malwares. We extracted DEX files from android applications and performed static analysis using class names and method names. This process doesn't not include reverse engineering, so it is possible to detect malwares efficiently.