Android malware are currently the only practical vector to bring security attacks to smartphone and tablets. Malware detection and prevention of zero day attacks requires a prompt analysis, which would benefit in terms of timeliness and accuracy, from being collaborative. This paper presents D-BRIDEMAID a reputation-based framework able to analyse Android applications, with the aim to exploit an hybrid static/dynamic framework for malware analysis to initiate a distributed app evaluation, involving real users willing to test the security features of an app on their device. This work focuses on the definition of the collaborative protocol, the reputation based incentive system and the models to compute revenue for users and security of apps. Simulative and real world experiments are presented to validate the model.
D-bridemaid: A distributed framework for collaborative and dynamic analysis of android malware
Mercaldo F.
;
2020-01-01
Abstract
Android malware are currently the only practical vector to bring security attacks to smartphone and tablets. Malware detection and prevention of zero day attacks requires a prompt analysis, which would benefit in terms of timeliness and accuracy, from being collaborative. This paper presents D-BRIDEMAID a reputation-based framework able to analyse Android applications, with the aim to exploit an hybrid static/dynamic framework for malware analysis to initiate a distributed app evaluation, involving real users willing to test the security features of an app on their device. This work focuses on the definition of the collaborative protocol, the reputation based incentive system and the models to compute revenue for users and security of apps. Simulative and real world experiments are presented to validate the model.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.