Although the importance of mobile applications grows every day, recent vulnerability reports argue the application's deficiency to meet modern security standards. Testing strategies alleviate the problem by identifying security violations in software implementations. This paper proposes a novel testing methodology that applies state machine learning of mobile Android applications in combination with algorithms that discover attack paths in the learned state machine. The presence of an attack path evidences the existence of a vulnerability in the mobile application. We apply our methods to real-life apps and show that the novel methodology is capable of identifying vulnerabilities.

Original languageEnglish
Title of host publicationProceedings - 3rd IEEE European Symposium on Security and Privacy Workshops, EUROS&PW 2018
Place of PublicationLos Alamitos, CA
Number of pages10
ISBN (Electronic)978-1-5386-5445-3
Publication statusPublished - 2018
Event3rd IEEE European Symposium on Security and Privacy Workshops: EUROS&PW 2018 - London, United Kingdom
Duration: 24 Apr 201826 Apr 2018
Conference number: 3


Conference3rd IEEE European Symposium on Security and Privacy Workshops
CountryUnited Kingdom

    Research areas

  • mobile application security, model inference, State machine learning, vulnerability detection

ID: 46669217