With the prevalence of machine learning in malware defense,hackers have tried to attack machine learning models to evade detection.It is generally difficult to explore the details of malware detection models,hackers c...With the prevalence of machine learning in malware defense,hackers have tried to attack machine learning models to evade detection.It is generally difficult to explore the details of malware detection models,hackers can adopt fuzzing attack to manipulate the features of the malware closer to benign programs on the premise of retaining their functions.In this paper,attack and defense methods on malware detection models based on machine learning algorithms were studied.Firstly,we designed a fuzzing attack method by randomly modifying features to evade detection.The fuzzing attack can effectively descend the accuracy of machine learning model with single feature.Then an adversarial malware detection model MaliFuzz is proposed to defend fuzzing attack.Different from the ordinary single feature detection model,the combined features by static and dynamic analysis to improve the defense ability are used.The experiment results show that the adversarial malware detection model with combined features can deal with the attack.The methods designed in this paper have great significance in improving the security of malware detection models and have good application prospects.展开更多
As the risk of malware is sharply increasing in Android platform,Android malware detection has become an important research topic.Existing works have demonstrated that required permissions of Android applications are ...As the risk of malware is sharply increasing in Android platform,Android malware detection has become an important research topic.Existing works have demonstrated that required permissions of Android applications are valuable for malware analysis,but how to exploit those permission patterns for malware detection remains an open issue.In this paper,we introduce the contrasting permission patterns to characterize the essential differences between malwares and clean applications from the permission aspect Then a framework based on contrasting permission patterns is presented for Android malware detection.According to the proposed framework,an ensemble classifier,Enclamald,is further developed to detect whether an application is potentially malicious.Every contrasting permission pattern is acting as a weak classifier in Enclamald,and the weighted predictions of involved weak classifiers are aggregated to the final result.Experiments on real-world applications validate that the proposed Enclamald classifier outperforms commonly used classifiers for Android Malware Detection.展开更多
Security tools are rapidly developed as network security threat is becoming more and more serious.To overcome the fundamental limitation of traditional host-based anti-malware system which is likely to be deceived and...Security tools are rapidly developed as network security threat is becoming more and more serious.To overcome the fundamental limitation of traditional host-based anti-malware system which is likely to be deceived and attacked by malicious codes,VMM-based anti-malware systems have recently become a hot research field.In this article,the existing malware hiding technique is analyzed,and a detecting model for hidden process based on "In-VM" idea is also proposed.Based on this detecting model,a hidden process detection technology which is based on HOOK SwapContext on the VMM platform is also implemented successfully.This technology can guarantee the detecting method not to be attacked by malwares and also resist all the current process hiding technologies.In order to detect the malwares which use remote injection method to hide themselves,a method by hijacking sysenter instruction is also proposed.Experiments show that the proposed methods guarantee the isolation of virtual machines,can detect all malware samples,and just bring little performance loss.展开更多
文摘With the prevalence of machine learning in malware defense,hackers have tried to attack machine learning models to evade detection.It is generally difficult to explore the details of malware detection models,hackers can adopt fuzzing attack to manipulate the features of the malware closer to benign programs on the premise of retaining their functions.In this paper,attack and defense methods on malware detection models based on machine learning algorithms were studied.Firstly,we designed a fuzzing attack method by randomly modifying features to evade detection.The fuzzing attack can effectively descend the accuracy of machine learning model with single feature.Then an adversarial malware detection model MaliFuzz is proposed to defend fuzzing attack.Different from the ordinary single feature detection model,the combined features by static and dynamic analysis to improve the defense ability are used.The experiment results show that the adversarial malware detection model with combined features can deal with the attack.The methods designed in this paper have great significance in improving the security of malware detection models and have good application prospects.
基金This work was supported by Deakin Cyber Security Research Cluster National Natural Science Foundation of China under Grant Nos. 61304067 and 61202211 +1 种基金 Guangxi Key Laboratory of Trusted Software No. kx201325 the Fundamental Research Funds for the Central Universities under Grant No 31541311314.
文摘As the risk of malware is sharply increasing in Android platform,Android malware detection has become an important research topic.Existing works have demonstrated that required permissions of Android applications are valuable for malware analysis,but how to exploit those permission patterns for malware detection remains an open issue.In this paper,we introduce the contrasting permission patterns to characterize the essential differences between malwares and clean applications from the permission aspect Then a framework based on contrasting permission patterns is presented for Android malware detection.According to the proposed framework,an ensemble classifier,Enclamald,is further developed to detect whether an application is potentially malicious.Every contrasting permission pattern is acting as a weak classifier in Enclamald,and the weighted predictions of involved weak classifiers are aggregated to the final result.Experiments on real-world applications validate that the proposed Enclamald classifier outperforms commonly used classifiers for Android Malware Detection.
基金National High Technical Research and Development Program of China(863 Program)under Grant No. 2008AA01Z414
文摘Security tools are rapidly developed as network security threat is becoming more and more serious.To overcome the fundamental limitation of traditional host-based anti-malware system which is likely to be deceived and attacked by malicious codes,VMM-based anti-malware systems have recently become a hot research field.In this article,the existing malware hiding technique is analyzed,and a detecting model for hidden process based on "In-VM" idea is also proposed.Based on this detecting model,a hidden process detection technology which is based on HOOK SwapContext on the VMM platform is also implemented successfully.This technology can guarantee the detecting method not to be attacked by malwares and also resist all the current process hiding technologies.In order to detect the malwares which use remote injection method to hide themselves,a method by hijacking sysenter instruction is also proposed.Experiments show that the proposed methods guarantee the isolation of virtual machines,can detect all malware samples,and just bring little performance loss.
