The detection of software vulnerabilities written in C and C++languages takes a lot of attention and interest today.This paper proposes a new framework called DrCSE to improve software vulnerability detection.It uses ...The detection of software vulnerabilities written in C and C++languages takes a lot of attention and interest today.This paper proposes a new framework called DrCSE to improve software vulnerability detection.It uses an intelligent computation technique based on the combination of two methods:Rebalancing data and representation learning to analyze and evaluate the code property graph(CPG)of the source code for detecting abnormal behavior of software vulnerabilities.To do that,DrCSE performs a combination of 3 main processing techniques:(i)building the source code feature profiles,(ii)rebalancing data,and(iii)contrastive learning.In which,the method(i)extracts the source code’s features based on the vertices and edges of the CPG.The method of rebalancing data has the function of supporting the training process by balancing the experimental dataset.Finally,contrastive learning techniques learn the important features of the source code by finding and pulling similar ones together while pushing the outliers away.The experiment part of this paper demonstrates the superiority of the DrCSE Framework for detecting source code security vulnerabilities using the Verum dataset.As a result,the method proposed in the article has brought a pretty good performance in all metrics,especially the Precision and Recall scores of 39.35%and 69.07%,respectively,proving the efficiency of the DrCSE Framework.It performs better than other approaches,with a 5%boost in Precision and a 5%boost in Recall.Overall,this is considered the best research result for the software vulnerability detection problem using the Verum dataset according to our survey to date.展开更多
The beach studied in this paper spans a length of 51 km and is one of several long sandy beaches in the southern Bohai Strait. Due to the obstruction of islands in the northeast and the influence of the underwater top...The beach studied in this paper spans a length of 51 km and is one of several long sandy beaches in the southern Bohai Strait. Due to the obstruction of islands in the northeast and the influence of the underwater topography, the wave environment in the offshore area is complex; beach types and sediment transport characteristics vary along different coasts. The coastlines extracted from six aerial photographs in different years were compared to demonstrate the evolving features. Seven typical beach profiles were selected to study the lateral beach variation characteristics. Continuous wind and wave observation data from Beihuangcheng ocean station during 2009 were employed for the hindcast of the local wave environment using a regional spectral wave model. Then the results of the wave hindcast were incorporated into the LITDRIFT model to compute the sediment transport rates and directions along the coasts and analyze the longshore sand movement. The results show that the coastline evolution of sand beaches in the southern Bohai Strait has spatial and temporal variations and the coast can be divided into four typical regions. Region (1), the north coast of Qimudao, is a slightly eroded and dissipative beach with a large sediment transport rate; Region (II), the southwest coast of Gangluan Port, is a slightly deposited and dissipative beach with moderate sediment transport rate; Region (III), in the central area, is a beach that is gradually transformed from a slightly eroded dissipative beach to a moderately or slightly strong eroded bar-trough beach from west to east with a relatively moderate sediment transport rate. Region (IV), on the east coast, is a strongly eroded and reflective beach with a weak sediment transport rate. The wave conditions exhibit an increasing trend from west to east in the off- shore area. The distribution of the wave-induced current inside the wave breaking region and the littoral sediment transport in the nearshore region exhibit a gradual weakening tendency from west to east, which is opposite to the trend of the wave conditions out- side the breaking region. The presence of submerged shoal (Dengzhou Shoal), deep trough (Dengzhou Channel), islands and irregu- lar topography influnces the wave climate, beach types, wave-induced current features, littoral sediment transport trends and coast- line evolution patterns in the southern Bohai Strait. Human activities, such as the sand exploitation of Dengzhou Shoal and other coastal engineering projects, also influence the beach morphology and coastline evolution.展开更多
文摘The detection of software vulnerabilities written in C and C++languages takes a lot of attention and interest today.This paper proposes a new framework called DrCSE to improve software vulnerability detection.It uses an intelligent computation technique based on the combination of two methods:Rebalancing data and representation learning to analyze and evaluate the code property graph(CPG)of the source code for detecting abnormal behavior of software vulnerabilities.To do that,DrCSE performs a combination of 3 main processing techniques:(i)building the source code feature profiles,(ii)rebalancing data,and(iii)contrastive learning.In which,the method(i)extracts the source code’s features based on the vertices and edges of the CPG.The method of rebalancing data has the function of supporting the training process by balancing the experimental dataset.Finally,contrastive learning techniques learn the important features of the source code by finding and pulling similar ones together while pushing the outliers away.The experiment part of this paper demonstrates the superiority of the DrCSE Framework for detecting source code security vulnerabilities using the Verum dataset.As a result,the method proposed in the article has brought a pretty good performance in all metrics,especially the Precision and Recall scores of 39.35%and 69.07%,respectively,proving the efficiency of the DrCSE Framework.It performs better than other approaches,with a 5%boost in Precision and a 5%boost in Recall.Overall,this is considered the best research result for the software vulnerability detection problem using the Verum dataset according to our survey to date.
基金supported by the National Natural Science Foundation for the Youth(No.41106039)
文摘The beach studied in this paper spans a length of 51 km and is one of several long sandy beaches in the southern Bohai Strait. Due to the obstruction of islands in the northeast and the influence of the underwater topography, the wave environment in the offshore area is complex; beach types and sediment transport characteristics vary along different coasts. The coastlines extracted from six aerial photographs in different years were compared to demonstrate the evolving features. Seven typical beach profiles were selected to study the lateral beach variation characteristics. Continuous wind and wave observation data from Beihuangcheng ocean station during 2009 were employed for the hindcast of the local wave environment using a regional spectral wave model. Then the results of the wave hindcast were incorporated into the LITDRIFT model to compute the sediment transport rates and directions along the coasts and analyze the longshore sand movement. The results show that the coastline evolution of sand beaches in the southern Bohai Strait has spatial and temporal variations and the coast can be divided into four typical regions. Region (1), the north coast of Qimudao, is a slightly eroded and dissipative beach with a large sediment transport rate; Region (II), the southwest coast of Gangluan Port, is a slightly deposited and dissipative beach with moderate sediment transport rate; Region (III), in the central area, is a beach that is gradually transformed from a slightly eroded dissipative beach to a moderately or slightly strong eroded bar-trough beach from west to east with a relatively moderate sediment transport rate. Region (IV), on the east coast, is a strongly eroded and reflective beach with a weak sediment transport rate. The wave conditions exhibit an increasing trend from west to east in the off- shore area. The distribution of the wave-induced current inside the wave breaking region and the littoral sediment transport in the nearshore region exhibit a gradual weakening tendency from west to east, which is opposite to the trend of the wave conditions out- side the breaking region. The presence of submerged shoal (Dengzhou Shoal), deep trough (Dengzhou Channel), islands and irregu- lar topography influnces the wave climate, beach types, wave-induced current features, littoral sediment transport trends and coast- line evolution patterns in the southern Bohai Strait. Human activities, such as the sand exploitation of Dengzhou Shoal and other coastal engineering projects, also influence the beach morphology and coastline evolution.