Behavioral and dynamic security functions chaining for Android devices

We present an approach for dynamically outsourcing and composing security functions for mobile devices, according to the network behavior of their running applications. Applications are characterized from a network point of view using data mining and clustering techniques with the aim to select their appropriate security functions. Software-defined networking mechanisms are employed to chain the selected functions and to redirect mobile apps traffic through the resulting security compositions. Those ones can be fully outsourced or split between in-cloud and on-device. Both a prototype and extensive simulations demonstrate the feasibility of the approach and assess its benefits.