Objective To characterize Chinese families in which both parents and at least one child are diagnosed with malignant diseases and provide reference for cancer screening or early detection in people whose both parents ...Objective To characterize Chinese families in which both parents and at least one child are diagnosed with malignant diseases and provide reference for cancer screening or early detection in people whose both parents are diagnosed with cancer.Methods Medical records of all clients to the center of cancer screening and prevention of the National Cancer Center/Cancer Hospital between January 2008 and February 2018 were screened to select families in which both parents and at least one child were diagnosed with malignant diseases.The cancer profiles of fathers,mothers,sons and daughters,their age distribution at diagnosis,and similarity of cancers between two generations were analyzed.The proportions of each cancer in males and females of the cohort were compared with corresponding data from the National Cancer Center Registry of China(NCCRC)in 2013.Results Totally 13S families were identified from records of 33200 clients.Proportion of lung cancer in fathers(40/135,29.6%)and in mothers(38/135,28.1%)were higher than the national data(23.9%in males and 14.9%in females,respectively).The proportion of breast cancer in daughters(35/109,32.1%)was higher than that of mothers(14/135,10.4%)and the national data(17.1%),In 71 father-son pairs of cancer,46.5%(33/71)were of the same systematic disease,and 16.9%(12/71)were of the same cancer.These two indexes were 31.2%(n=34)and 10.1%(n=l 1),respectively in the 109 father-daughter pairs of cancer,36.6%(n=26)and 8.5%(n=6)respectively in the 71 mother-son pairs of cancer,and 31.2%(n=34)and 20.2%(n=20)respectively in the 109 mother-daughter pairs of cancer.Sons were more likely to suffer from cancers originated from the same system as father s cancer than daughters(χ^(2)=4.299,P<0.05),and daughters were more likely to suffer from the same cancer as their mother's cancer than sons(χ^(2)=4.506,P<0.05).The age(mean±standard deviation)of the daughters(52.4±12.7)and the sons(59.4±10.9)at diagnosis were significantly younger than the fathers(65.5±12.2)and the mothers(65.7±12.5)(al展开更多
Power Shell has been widely deployed in fileless malware and advanced persistent threat(APT)attacks due to its high stealthiness and live-off-theland technique.However,existing works mainly focus on deobfuscation and ...Power Shell has been widely deployed in fileless malware and advanced persistent threat(APT)attacks due to its high stealthiness and live-off-theland technique.However,existing works mainly focus on deobfuscation and malicious detection,lacking the malicious Power Shell families classification and behavior analysis.Moreover,the state-of-the-art methods fail to capture fine-grained features and semantic relationships,resulting in low robustness and accuracy.To this end,we propose Power Detector,a novel malicious Power Shell script detector based on multimodal semantic fusion and deep learning.Specifically,we design four feature extraction methods to extract key features from character,token,abstract syntax tree(AST),and semantic knowledge graph.Then,we intelligently design four embeddings(i.e.,Char2Vec,Token2Vec,AST2Vec,and Rela2Vec) and construct a multi-modal fusion algorithm to concatenate feature vectors from different views.Finally,we propose a combined model based on transformer and CNN-Bi LSTM to implement Power Shell family detection.Our experiments with five types of Power Shell attacks show that PowerDetector can accurately detect various obfuscated and stealth PowerShell scripts,with a 0.9402 precision,a 0.9358 recall,and a 0.9374 F1-score.Furthermore,through singlemodal and multi-modal comparison experiments,we demonstrate that PowerDetector’s multi-modal embedding and deep learning model can achieve better accuracy and even identify more unknown attacks.展开更多
基金the National Key R&D Program of China(2017YFC1308700)Peking Union Medical College Discipline Development Project(201920200303).
文摘Objective To characterize Chinese families in which both parents and at least one child are diagnosed with malignant diseases and provide reference for cancer screening or early detection in people whose both parents are diagnosed with cancer.Methods Medical records of all clients to the center of cancer screening and prevention of the National Cancer Center/Cancer Hospital between January 2008 and February 2018 were screened to select families in which both parents and at least one child were diagnosed with malignant diseases.The cancer profiles of fathers,mothers,sons and daughters,their age distribution at diagnosis,and similarity of cancers between two generations were analyzed.The proportions of each cancer in males and females of the cohort were compared with corresponding data from the National Cancer Center Registry of China(NCCRC)in 2013.Results Totally 13S families were identified from records of 33200 clients.Proportion of lung cancer in fathers(40/135,29.6%)and in mothers(38/135,28.1%)were higher than the national data(23.9%in males and 14.9%in females,respectively).The proportion of breast cancer in daughters(35/109,32.1%)was higher than that of mothers(14/135,10.4%)and the national data(17.1%),In 71 father-son pairs of cancer,46.5%(33/71)were of the same systematic disease,and 16.9%(12/71)were of the same cancer.These two indexes were 31.2%(n=34)and 10.1%(n=l 1),respectively in the 109 father-daughter pairs of cancer,36.6%(n=26)and 8.5%(n=6)respectively in the 71 mother-son pairs of cancer,and 31.2%(n=34)and 20.2%(n=20)respectively in the 109 mother-daughter pairs of cancer.Sons were more likely to suffer from cancers originated from the same system as father s cancer than daughters(χ^(2)=4.299,P<0.05),and daughters were more likely to suffer from the same cancer as their mother's cancer than sons(χ^(2)=4.506,P<0.05).The age(mean±standard deviation)of the daughters(52.4±12.7)and the sons(59.4±10.9)at diagnosis were significantly younger than the fathers(65.5±12.2)and the mothers(65.7±12.5)(al
基金This work was supported by National Natural Science Foundation of China(No.62172308,No.U1626107,No.61972297,No.62172144,and No.62062019).
文摘Power Shell has been widely deployed in fileless malware and advanced persistent threat(APT)attacks due to its high stealthiness and live-off-theland technique.However,existing works mainly focus on deobfuscation and malicious detection,lacking the malicious Power Shell families classification and behavior analysis.Moreover,the state-of-the-art methods fail to capture fine-grained features and semantic relationships,resulting in low robustness and accuracy.To this end,we propose Power Detector,a novel malicious Power Shell script detector based on multimodal semantic fusion and deep learning.Specifically,we design four feature extraction methods to extract key features from character,token,abstract syntax tree(AST),and semantic knowledge graph.Then,we intelligently design four embeddings(i.e.,Char2Vec,Token2Vec,AST2Vec,and Rela2Vec) and construct a multi-modal fusion algorithm to concatenate feature vectors from different views.Finally,we propose a combined model based on transformer and CNN-Bi LSTM to implement Power Shell family detection.Our experiments with five types of Power Shell attacks show that PowerDetector can accurately detect various obfuscated and stealth PowerShell scripts,with a 0.9402 precision,a 0.9358 recall,and a 0.9374 F1-score.Furthermore,through singlemodal and multi-modal comparison experiments,we demonstrate that PowerDetector’s multi-modal embedding and deep learning model can achieve better accuracy and even identify more unknown attacks.
