加密型勒索软件通过加密用户文件来勒索赎金.现有的基于第一条加密应用编程接口(Application Programming Interface,API)的早期检测方法无法在勒索软件执行加密行为前将其检出.由于不同家族的勒索软件开始执行其加密行为的时刻各不相同...加密型勒索软件通过加密用户文件来勒索赎金.现有的基于第一条加密应用编程接口(Application Programming Interface,API)的早期检测方法无法在勒索软件执行加密行为前将其检出.由于不同家族的勒索软件开始执行其加密行为的时刻各不相同,现有的基于固定时间阈值的早期检测方法仅能将少量勒索软件在其执行加密行为前准确检出.为进一步提升勒索软件检测的及时性,本文在分析多款勒索软件运行初期调用动态链接库(Dynamic Link Library,DLL)和API行为的基础上,提出了一个表征软件从开始运行到首次调用加密相关DLL之间的时间段的概念——运行初始阶段(Initial Phase of Operation,IPO),并提出了一个以软件在IPO内产生的API序列为检测对象的勒索软件早期检测方法,即基于API潜在语义的勒索软件早期检测方法(Ransomware Early Detection Method based on API Latent Semantics,REDMALS).REDMALS采集IPO内的API序列后,采用TF-IDF(Term Frequency-Inverse Document Frequency)算法以及潜在语义分析(Latent Semantic Analysis,LSA)算法对采集的API序列生成特征向量及提取潜在的语义结构,再运用机器学习算法构建检测模型用于勒索软件检测.实验结果显示运用随机森林算法的REDMALS在构建的变种测试集和未知测试集上可分别获得97.7%、96.0%的准确率,且两个测试集中83%和76%的勒索软件样本可在其执行加密行为前被检出.展开更多
logical testing model and resource lifecycle information,generate test cases and complete parameters,and alleviate inconsistency issues through parameter inference.Once again,we propose a method of analyzing test resu...logical testing model and resource lifecycle information,generate test cases and complete parameters,and alleviate inconsistency issues through parameter inference.Once again,we propose a method of analyzing test results using joint state codes and call stack information,which compensates for the shortcomings of traditional analysis methods.We will apply our method to testing REST services,including OpenStack,an open source cloud operating platform for experimental evaluation.We have found a series of inconsistencies,known vulnerabilities,and new unknown logical defects.展开更多
The Cap Pushing Response (CPR) is a free-flying technique used to study learning and memory in honey bees (Apis mellifera). The series of experiments outlined in this paper aimed to test whether honey bees exhibit the...The Cap Pushing Response (CPR) is a free-flying technique used to study learning and memory in honey bees (Apis mellifera). The series of experiments outlined in this paper aimed to test whether honey bees exhibit the cognitive concept of “expectancy” utilizing the CPR in a weight differentiation paradigm. Five previous experiments in our laboratory have explored whether the concept of expectancy can account for honey bee performance and have all failed to support the cognitive interpretation. The first experiment examined if bees could differentiate between the two caps in the amount of force they used to push the cap and the distance the cap was pushed when the caps were presented one at a time. The second experiment explored cap weight preference by presenting bees with a choice between the two caps. The third and fourth experiments tested the bee’s ability to expect reward or punishment based on cap weight. Results revealed that bees were found to have a strong preference for the light cap and therefore were not able to expect reward or punishment based on cap weight. These experiments contribute to the debate on whether bees have “cognitive” representations and continue to support the behaviorist interpretation.展开更多
软件开发者在开发过程遇到应用程序编程接口(application programming interface,API)使用问题时,通常希望能够得到有效的API使用模式建议,从而帮助其学习和使用.传统的API推荐方法会挖掘和学习代码库中API的使用知识,然后给开发者推荐...软件开发者在开发过程遇到应用程序编程接口(application programming interface,API)使用问题时,通常希望能够得到有效的API使用模式建议,从而帮助其学习和使用.传统的API推荐方法会挖掘和学习代码库中API的使用知识,然后给开发者推荐与上下文相关的API.然而由于上下文信息表征不够充分,以及推荐列表中冗余项和同质化内容的出现影响了推荐性能.针对这一问题,构建项目和方法与API的API层次调用图(API hierarchy call graph,AHCG)模型以更好地表达API上下文关系,充分利用API结构信息和语义信息来减少冗余项和降低同质化内容被推荐的可能性,进而提出基于上下文感知并面向多样性的API推荐(context-aware based API recommendation with diversity,CAPIRD)方法.该方法中引入相关性度量和关联性度量,最大限度地保留相关结果,同时平衡已选API与候选API的关联性,以尽可能挖掘到合理的初选API列表.最后结合最大边缘相关算法,在标准模式数据集上学习相关性和关联性的最佳权重组合,并进行多样性重排推荐.在2210个项目构成的3类数据集上进行实验并验证推荐性能,实验结果表明,CAPIRD在基于上下文的API推荐场景下能够有效提高推荐性能.在所有数据集的API推荐中,平均精度(mean average precision,MAP)指标平均提升值约9%,在Top-1的推荐中,成功率(success rate)指标平均提升约13%.展开更多
文摘加密型勒索软件通过加密用户文件来勒索赎金.现有的基于第一条加密应用编程接口(Application Programming Interface,API)的早期检测方法无法在勒索软件执行加密行为前将其检出.由于不同家族的勒索软件开始执行其加密行为的时刻各不相同,现有的基于固定时间阈值的早期检测方法仅能将少量勒索软件在其执行加密行为前准确检出.为进一步提升勒索软件检测的及时性,本文在分析多款勒索软件运行初期调用动态链接库(Dynamic Link Library,DLL)和API行为的基础上,提出了一个表征软件从开始运行到首次调用加密相关DLL之间的时间段的概念——运行初始阶段(Initial Phase of Operation,IPO),并提出了一个以软件在IPO内产生的API序列为检测对象的勒索软件早期检测方法,即基于API潜在语义的勒索软件早期检测方法(Ransomware Early Detection Method based on API Latent Semantics,REDMALS).REDMALS采集IPO内的API序列后,采用TF-IDF(Term Frequency-Inverse Document Frequency)算法以及潜在语义分析(Latent Semantic Analysis,LSA)算法对采集的API序列生成特征向量及提取潜在的语义结构,再运用机器学习算法构建检测模型用于勒索软件检测.实验结果显示运用随机森林算法的REDMALS在构建的变种测试集和未知测试集上可分别获得97.7%、96.0%的准确率,且两个测试集中83%和76%的勒索软件样本可在其执行加密行为前被检出.
文摘logical testing model and resource lifecycle information,generate test cases and complete parameters,and alleviate inconsistency issues through parameter inference.Once again,we propose a method of analyzing test results using joint state codes and call stack information,which compensates for the shortcomings of traditional analysis methods.We will apply our method to testing REST services,including OpenStack,an open source cloud operating platform for experimental evaluation.We have found a series of inconsistencies,known vulnerabilities,and new unknown logical defects.
文摘The Cap Pushing Response (CPR) is a free-flying technique used to study learning and memory in honey bees (Apis mellifera). The series of experiments outlined in this paper aimed to test whether honey bees exhibit the cognitive concept of “expectancy” utilizing the CPR in a weight differentiation paradigm. Five previous experiments in our laboratory have explored whether the concept of expectancy can account for honey bee performance and have all failed to support the cognitive interpretation. The first experiment examined if bees could differentiate between the two caps in the amount of force they used to push the cap and the distance the cap was pushed when the caps were presented one at a time. The second experiment explored cap weight preference by presenting bees with a choice between the two caps. The third and fourth experiments tested the bee’s ability to expect reward or punishment based on cap weight. Results revealed that bees were found to have a strong preference for the light cap and therefore were not able to expect reward or punishment based on cap weight. These experiments contribute to the debate on whether bees have “cognitive” representations and continue to support the behaviorist interpretation.
文摘软件开发者在开发过程遇到应用程序编程接口(application programming interface,API)使用问题时,通常希望能够得到有效的API使用模式建议,从而帮助其学习和使用.传统的API推荐方法会挖掘和学习代码库中API的使用知识,然后给开发者推荐与上下文相关的API.然而由于上下文信息表征不够充分,以及推荐列表中冗余项和同质化内容的出现影响了推荐性能.针对这一问题,构建项目和方法与API的API层次调用图(API hierarchy call graph,AHCG)模型以更好地表达API上下文关系,充分利用API结构信息和语义信息来减少冗余项和降低同质化内容被推荐的可能性,进而提出基于上下文感知并面向多样性的API推荐(context-aware based API recommendation with diversity,CAPIRD)方法.该方法中引入相关性度量和关联性度量,最大限度地保留相关结果,同时平衡已选API与候选API的关联性,以尽可能挖掘到合理的初选API列表.最后结合最大边缘相关算法,在标准模式数据集上学习相关性和关联性的最佳权重组合,并进行多样性重排推荐.在2210个项目构成的3类数据集上进行实验并验证推荐性能,实验结果表明,CAPIRD在基于上下文的API推荐场景下能够有效提高推荐性能.在所有数据集的API推荐中,平均精度(mean average precision,MAP)指标平均提升值约9%,在Top-1的推荐中,成功率(success rate)指标平均提升约13%.