The prevalence of smartphones is deeply embedded in modern society,impacting various aspects of our lives.Their versatility and functionalities have fundamentally changed how we communicate,work,seek entertainment,and...The prevalence of smartphones is deeply embedded in modern society,impacting various aspects of our lives.Their versatility and functionalities have fundamentally changed how we communicate,work,seek entertainment,and access information.Among the many smartphones available,those operating on the Android platform dominate,being the most widely used type.This widespread adoption of the Android OS has significantly contributed to increased malware attacks targeting the Android ecosystem in recent years.Therefore,there is an urgent need to develop new methods for detecting Android malware.The literature contains numerous works related to Android malware detection.As far as our understanding extends,we are the first ones to identify dangerous combinations of permissions and system calls to uncover malicious behavior in Android applications.We introduce a novel methodology that pairs permissions and system calls to distinguish between benign and malicious samples.This approach combines the advantages of static and dynamic analysis,offering a more comprehensive understanding of an application’s behavior.We establish covalent bonds between permissions and system calls to assess their combined impact.We introduce a novel technique to determine these pairs’Covalent Bond Strength Score.Each pair is assigned two scores,one for malicious behavior and another for benign behavior.These scores serve as the basis for classifying applications as benign or malicious.By correlating permissions with system calls,the study enables a detailed examination of how an app utilizes its requested permissions,aiding in differentiating legitimate and potentially harmful actions.This comprehensive analysis provides a robust framework for Android malware detection,marking a significant contribution to the field.The results of our experiments demonstrate a remarkable overall accuracy of 97.5%,surpassing various state-of-the-art detection techniques proposed in the current literature.展开更多
Despite only being around for a few years, mobile devices have steadily risen to become the most extensively used computer devices. Given the number of people who rely on smartphones, which can install third-party app...Despite only being around for a few years, mobile devices have steadily risen to become the most extensively used computer devices. Given the number of people who rely on smartphones, which can install third-party apps, it has become an increasingly important issue for end-users and service providers to ensure that both the devices and the underlying network are secure. People will become more reliant on applications such as SMS, MMS, Internet Access, Online Transactions, and so on due to such features and capabilities. Thousands of devices ranging from low-cost phones to high-end luxury phones are powered by the Android operating system, which has dominated the smartphone marketplace. It is about making it possible for people from all socioeconomic backgrounds to get and use mobile devices in their daily activities. In response to this growing popularity, the number of new applications introduced to the Android market has skyrocketed. The recent appearance of a wide range of mobile malware has caught the attention of security professionals and scholars alike. In light of the ongoing expansion of the mobile phone industry, the likelihood of it being used in criminal activities will only continue to rise in the future. This article reviews the literature on malware detection and prevention in Android mobile devices, analyzes the existing literature on major studies and tasks, and covers articles, journals, and digital resources such as Internet security publications, scientific studies, and conferences.展开更多
隐私政策文档声明了应用程序需要获取的隐私信息,但不能保证清晰且完全披露应用获取的隐私信息类型,目前对应用实际敏感行为与隐私政策一致性分析的研究仍存在不足。针对上述问题,提出一种Android应用敏感行为与隐私政策一致性分析方法...隐私政策文档声明了应用程序需要获取的隐私信息,但不能保证清晰且完全披露应用获取的隐私信息类型,目前对应用实际敏感行为与隐私政策一致性分析的研究仍存在不足。针对上述问题,提出一种Android应用敏感行为与隐私政策一致性分析方法。在隐私政策分析阶段,基于Bi-GRU-CRF(Bi-directional Gated Recurrent Unit Conditional Random Field)神经网络,通过添加自定义标注库对模型进行增量训练,实现对隐私政策声明中的关键信息的提取;在敏感行为分析阶段,通过对敏感应用程序接口(API)调用进行分类、对输入敏感源列表中已分析过的敏感API调用进行删除,以及对已提取过的敏感路径进行标记的方法来优化IFDS(Interprocedural,Finite,Distributive,Subset)算法,使敏感行为分析结果与隐私政策描述的语言粒度相匹配,并且降低分析结果的冗余,提高分析效率;在一致性分析阶段,将本体之间的语义关系分为等价关系、从属关系和近似关系,并据此定义敏感行为与隐私政策一致性形式化模型,将敏感行为与隐私政策一致的情况分为清晰的表述和模糊的表述,将不一致的情况分为省略的表述、不正确的表述和有歧义的表述,最后根据所提基于语义相似度的一致性分析算法对敏感行为与隐私政策进行一致性分析。实验结果表明,对928个应用程序进行分析,在隐私政策分析正确率为97.34%的情况下,51.4%的Android应用程序存在应用实际敏感行为与隐私政策声明不一致的情况。展开更多
The growing usage of Android smartphones has led to a significant rise in incidents of Android malware andprivacy breaches.This escalating security concern necessitates the development of advanced technologies capable...The growing usage of Android smartphones has led to a significant rise in incidents of Android malware andprivacy breaches.This escalating security concern necessitates the development of advanced technologies capableof automatically detecting andmitigatingmalicious activities in Android applications(apps).Such technologies arecrucial for safeguarding user data and maintaining the integrity of mobile devices in an increasingly digital world.Current methods employed to detect sensitive data leaks in Android apps are hampered by two major limitationsthey require substantial computational resources and are prone to a high frequency of false positives.This meansthat while attempting to identify security breaches,these methods often consume considerable processing powerand mistakenly flag benign activities as malicious,leading to inefficiencies and reduced reliability in malwaredetection.The proposed approach includes a data preprocessing step that removes duplicate samples,managesunbalanced datasets,corrects inconsistencies,and imputes missing values to ensure data accuracy.The Minimaxmethod is then used to normalize numerical data,followed by feature vector extraction using the Gain ratio andChi-squared test to identify and extract the most significant characteristics using an appropriate prediction model.This study focuses on extracting a subset of attributes best suited for the task and recommending a predictivemodel based on domain expert opinion.The proposed method is evaluated using Drebin and TUANDROMDdatasets containing 15,036 and 4,464 benign and malicious samples,respectively.The empirical result shows thatthe RandomForest(RF)and Support VectorMachine(SVC)classifiers achieved impressive accuracy rates of 98.9%and 98.8%,respectively,in detecting unknown Androidmalware.A sensitivity analysis experiment was also carriedout on all three ML-based classifiers based on MAE,MSE,R2,and sensitivity parameters,resulting in a flawlessperformance for both datasets.This approach has substantial potential for real-world applications and can serve asa valuable tool for preventing the spread of Androidmalware and enhancing mobile device security.展开更多
文摘The prevalence of smartphones is deeply embedded in modern society,impacting various aspects of our lives.Their versatility and functionalities have fundamentally changed how we communicate,work,seek entertainment,and access information.Among the many smartphones available,those operating on the Android platform dominate,being the most widely used type.This widespread adoption of the Android OS has significantly contributed to increased malware attacks targeting the Android ecosystem in recent years.Therefore,there is an urgent need to develop new methods for detecting Android malware.The literature contains numerous works related to Android malware detection.As far as our understanding extends,we are the first ones to identify dangerous combinations of permissions and system calls to uncover malicious behavior in Android applications.We introduce a novel methodology that pairs permissions and system calls to distinguish between benign and malicious samples.This approach combines the advantages of static and dynamic analysis,offering a more comprehensive understanding of an application’s behavior.We establish covalent bonds between permissions and system calls to assess their combined impact.We introduce a novel technique to determine these pairs’Covalent Bond Strength Score.Each pair is assigned two scores,one for malicious behavior and another for benign behavior.These scores serve as the basis for classifying applications as benign or malicious.By correlating permissions with system calls,the study enables a detailed examination of how an app utilizes its requested permissions,aiding in differentiating legitimate and potentially harmful actions.This comprehensive analysis provides a robust framework for Android malware detection,marking a significant contribution to the field.The results of our experiments demonstrate a remarkable overall accuracy of 97.5%,surpassing various state-of-the-art detection techniques proposed in the current literature.
文摘Despite only being around for a few years, mobile devices have steadily risen to become the most extensively used computer devices. Given the number of people who rely on smartphones, which can install third-party apps, it has become an increasingly important issue for end-users and service providers to ensure that both the devices and the underlying network are secure. People will become more reliant on applications such as SMS, MMS, Internet Access, Online Transactions, and so on due to such features and capabilities. Thousands of devices ranging from low-cost phones to high-end luxury phones are powered by the Android operating system, which has dominated the smartphone marketplace. It is about making it possible for people from all socioeconomic backgrounds to get and use mobile devices in their daily activities. In response to this growing popularity, the number of new applications introduced to the Android market has skyrocketed. The recent appearance of a wide range of mobile malware has caught the attention of security professionals and scholars alike. In light of the ongoing expansion of the mobile phone industry, the likelihood of it being used in criminal activities will only continue to rise in the future. This article reviews the literature on malware detection and prevention in Android mobile devices, analyzes the existing literature on major studies and tasks, and covers articles, journals, and digital resources such as Internet security publications, scientific studies, and conferences.
文摘隐私政策文档声明了应用程序需要获取的隐私信息,但不能保证清晰且完全披露应用获取的隐私信息类型,目前对应用实际敏感行为与隐私政策一致性分析的研究仍存在不足。针对上述问题,提出一种Android应用敏感行为与隐私政策一致性分析方法。在隐私政策分析阶段,基于Bi-GRU-CRF(Bi-directional Gated Recurrent Unit Conditional Random Field)神经网络,通过添加自定义标注库对模型进行增量训练,实现对隐私政策声明中的关键信息的提取;在敏感行为分析阶段,通过对敏感应用程序接口(API)调用进行分类、对输入敏感源列表中已分析过的敏感API调用进行删除,以及对已提取过的敏感路径进行标记的方法来优化IFDS(Interprocedural,Finite,Distributive,Subset)算法,使敏感行为分析结果与隐私政策描述的语言粒度相匹配,并且降低分析结果的冗余,提高分析效率;在一致性分析阶段,将本体之间的语义关系分为等价关系、从属关系和近似关系,并据此定义敏感行为与隐私政策一致性形式化模型,将敏感行为与隐私政策一致的情况分为清晰的表述和模糊的表述,将不一致的情况分为省略的表述、不正确的表述和有歧义的表述,最后根据所提基于语义相似度的一致性分析算法对敏感行为与隐私政策进行一致性分析。实验结果表明,对928个应用程序进行分析,在隐私政策分析正确率为97.34%的情况下,51.4%的Android应用程序存在应用实际敏感行为与隐私政策声明不一致的情况。
基金Princess Nourah bint Abdulrahman University and Researchers Supporting Project Number(PNURSP2024R346)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘The growing usage of Android smartphones has led to a significant rise in incidents of Android malware andprivacy breaches.This escalating security concern necessitates the development of advanced technologies capableof automatically detecting andmitigatingmalicious activities in Android applications(apps).Such technologies arecrucial for safeguarding user data and maintaining the integrity of mobile devices in an increasingly digital world.Current methods employed to detect sensitive data leaks in Android apps are hampered by two major limitationsthey require substantial computational resources and are prone to a high frequency of false positives.This meansthat while attempting to identify security breaches,these methods often consume considerable processing powerand mistakenly flag benign activities as malicious,leading to inefficiencies and reduced reliability in malwaredetection.The proposed approach includes a data preprocessing step that removes duplicate samples,managesunbalanced datasets,corrects inconsistencies,and imputes missing values to ensure data accuracy.The Minimaxmethod is then used to normalize numerical data,followed by feature vector extraction using the Gain ratio andChi-squared test to identify and extract the most significant characteristics using an appropriate prediction model.This study focuses on extracting a subset of attributes best suited for the task and recommending a predictivemodel based on domain expert opinion.The proposed method is evaluated using Drebin and TUANDROMDdatasets containing 15,036 and 4,464 benign and malicious samples,respectively.The empirical result shows thatthe RandomForest(RF)and Support VectorMachine(SVC)classifiers achieved impressive accuracy rates of 98.9%and 98.8%,respectively,in detecting unknown Androidmalware.A sensitivity analysis experiment was also carriedout on all three ML-based classifiers based on MAE,MSE,R2,and sensitivity parameters,resulting in a flawlessperformance for both datasets.This approach has substantial potential for real-world applications and can serve asa valuable tool for preventing the spread of Androidmalware and enhancing mobile device security.
