# Yes, Machine Learning Can Be More Secure! A Case Study on Android Malware Detection

## TL;DR

This paper evaluates the vulnerabilities of machine learning-based Android malware detection and proposes a scalable secure-learning approach to mitigate evasion attacks, balancing security and detection performance.

## Contribution

It introduces a simple, scalable secure-learning paradigm that reduces evasion attack success while maintaining detection accuracy, applicable to various malware detection tasks.

## Key findings

- Assessment of attack scenarios against Drebin malware detector
- Implementation of evasion attacks demonstrating vulnerabilities
- Proposed secure-learning method improves robustness with minimal detection loss

## Abstract

To cope with the increasing variability and sophistication of modern attacks, machine learning has been widely adopted as a statistically-sound tool for malware detection. However, its security against well-crafted attacks has not only been recently questioned, but it has been shown that machine learning exhibits inherent vulnerabilities that can be exploited to evade detection at test time. In other words, machine learning itself can be the weakest link in a security system. In this paper, we rely upon a previously-proposed attack framework to categorize potential attack scenarios against learning-based malware detection tools, by modeling attackers with different skills and capabilities. We then define and implement a set of corresponding evasion attacks to thoroughly assess the security of Drebin, an Android malware detector. The main contribution of this work is the proposal of a simple and scalable secure-learning paradigm that mitigates the impact of evasion attacks, while only slightly worsening the detection rate in the absence of attack. We finally argue that our secure-learning approach can also be readily applied to other malware detection tasks.