MLNS2

Machine Learning, Network, System and Security

 

Principal investigators

  • Bernabé Batchakui, University of Yaounde I, Cameroon
  • David Bromberg, WIDE research team, Inria Grenoble – Rhône-Alpes

Abstract

Nowadays there are no satisfactory solutions to stop the proliferation of: (i) simboxes, and (ii) malware over Android devices. They constitute a severe threat to any businesses. In one hand, simboxes enable massive interconnect bypass frauds, and hence provide low cost international calls while leveraging cellular networks from telecom operators without their authorization. In another hand, malware may interrupt and disable applications, retrieve and spoof personal information and identity, access sensitive information, control all applications executing on users’ device, and even overcharge users for functionality that is widely available. The aim of this collaboration is to tackle the two aforementioned challenges from a system perspective. In particular we aim to adequately design and investigate efficient techniques to fight against simbox frauds and malware proliferation. Addressing such challenges require multidisciplinary knowledge such as Machine Learning, Network, System, and Security (MLNS2). Having these four areas of expertise in the same research team is rare, and this is one of the strengths of this collaboration. Our scientific goal is to bridge the gap between each of these four areas of expertise while leveraging our ongoing joint works.

Key words: software security, operating system, privacy, mobile systems

Website: in progress

Comments are closed.