In the context of modern software development characterized by increasing complexity and compressed development cycles,traditional static vulnerability detection methods face prominent challenges including high false ...In the context of modern software development characterized by increasing complexity and compressed development cycles,traditional static vulnerability detection methods face prominent challenges including high false positive rates and missed detections of complex logic due to their over-reliance on rule templates.This paper proposes a Syntax-Aware Hierarchical Attention Network(SAHAN)model,which achieves high-precision vulnerability detection through grammar-rule-driven multi-granularity code slicing and hierarchical semantic fusion mechanisms.The SAHAN model first generates Syntax Independent Units(SIUs),which slices the code based on Abstract Syntax Tree(AST)and predefined grammar rules,retaining vulnerability-sensitive contexts.Following this,through a hierarchical attention mechanism,the local syntax-aware layer encodes fine-grained patterns within SIUs,while the global semantic correlation layer captures vulnerability chains across SIUs,achieving synergistic modeling of syntax and semantics.Experiments show that on benchmark datasets like QEMU,SAHAN significantly improves detection performance by 4.8%to 13.1%on average compared to baseline models such as Devign and VulDeePecker.展开更多
Frequent glacier-related watershed geohazard chains are causing severe damage to life and infrastructure,reported consistently from the Eastern Himalayan Syntaxis.This paper presents a systematic method for researchin...Frequent glacier-related watershed geohazard chains are causing severe damage to life and infrastructure,reported consistently from the Eastern Himalayan Syntaxis.This paper presents a systematic method for researching geohazard,from regional to individual scale.The methodology includes the establishment of geological chain inventories,discrimination of geohazard chain modes,analyses of dynamics and dam breaches,and risk assessments.The following results were obtained:(1)In the downstream of Yarlung Zangbo River,175 sites were identified as high-risk for river blockage disasters,indicating the development of watershed geohazards.Five geohazard chain modes were summarized by incorporating geomorphological characteristics,historical events,landslide zoning,and materials.The risk areas of typical hazard were identified and assessed using InSAR data.(2)Glacier-related watershed geohazard chains are significantly different from traditional landslides.A detailed inversion analysis was conducted on the massive rock-ice avalanche in the Sedongpu gully in 2021.This particular event lasted roughly 300 seconds,with a maximum flow velocity of 77.2 m/s and a maximum flow height of 93 meters.By scrutinizing the dynamic processes and mechanical characteristics,mobility stages and phase transitions can be divided into four stages.(3)Watershed geohazard chains tend to block rivers.The peak breach discharge of the Yigong Landslide reached 12.4×10^(4) m^(3)/s,which is 36 times the volume of the seasonal flood discharge in the Yigong River.Megafloods caused by landslide dam breaches have significantly shaped the geomorphology.This study offers insights into disaster patterns and the multistaged movement characteristics of glacier-related watershed geohazard chains,providing a comprehensive method for investigations and assessments in glacial regions.展开更多
基金supported by the research start-up funds for invited doctor of Lanzhou University of Technology under Grant 14/062402。
文摘In the context of modern software development characterized by increasing complexity and compressed development cycles,traditional static vulnerability detection methods face prominent challenges including high false positive rates and missed detections of complex logic due to their over-reliance on rule templates.This paper proposes a Syntax-Aware Hierarchical Attention Network(SAHAN)model,which achieves high-precision vulnerability detection through grammar-rule-driven multi-granularity code slicing and hierarchical semantic fusion mechanisms.The SAHAN model first generates Syntax Independent Units(SIUs),which slices the code based on Abstract Syntax Tree(AST)and predefined grammar rules,retaining vulnerability-sensitive contexts.Following this,through a hierarchical attention mechanism,the local syntax-aware layer encodes fine-grained patterns within SIUs,while the global semantic correlation layer captures vulnerability chains across SIUs,achieving synergistic modeling of syntax and semantics.Experiments show that on benchmark datasets like QEMU,SAHAN significantly improves detection performance by 4.8%to 13.1%on average compared to baseline models such as Devign and VulDeePecker.
基金supported by the National Natural Science Foundation of China(Nos.U2244227,U2244226,42177172)the National Key R&D Program of China(No.2022YFC3004301)China Geological Survey Project(No.DD20230538)。
文摘Frequent glacier-related watershed geohazard chains are causing severe damage to life and infrastructure,reported consistently from the Eastern Himalayan Syntaxis.This paper presents a systematic method for researching geohazard,from regional to individual scale.The methodology includes the establishment of geological chain inventories,discrimination of geohazard chain modes,analyses of dynamics and dam breaches,and risk assessments.The following results were obtained:(1)In the downstream of Yarlung Zangbo River,175 sites were identified as high-risk for river blockage disasters,indicating the development of watershed geohazards.Five geohazard chain modes were summarized by incorporating geomorphological characteristics,historical events,landslide zoning,and materials.The risk areas of typical hazard were identified and assessed using InSAR data.(2)Glacier-related watershed geohazard chains are significantly different from traditional landslides.A detailed inversion analysis was conducted on the massive rock-ice avalanche in the Sedongpu gully in 2021.This particular event lasted roughly 300 seconds,with a maximum flow velocity of 77.2 m/s and a maximum flow height of 93 meters.By scrutinizing the dynamic processes and mechanical characteristics,mobility stages and phase transitions can be divided into four stages.(3)Watershed geohazard chains tend to block rivers.The peak breach discharge of the Yigong Landslide reached 12.4×10^(4) m^(3)/s,which is 36 times the volume of the seasonal flood discharge in the Yigong River.Megafloods caused by landslide dam breaches have significantly shaped the geomorphology.This study offers insights into disaster patterns and the multistaged movement characteristics of glacier-related watershed geohazard chains,providing a comprehensive method for investigations and assessments in glacial regions.
