# Adversarial Samples on Android Malware Detection Systems for IoT Systems

## TL;DR

This paper introduces TLAMD, a genetic algorithm-based testing framework that effectively generates adversarial samples to evaluate the robustness of Android malware detection systems in IoT devices, achieving nearly 100% success rate.

## Contribution

The paper presents a novel testing framework for IoT Android malware detection systems that does not require model training parameters and is effective in black-box scenarios.

## Key findings

- Achieves nearly 100% success rate in generating adversarial samples.
- Enables black-box testing of Android malware detection systems.
- Uses genetic algorithms to optimize adversarial sample generation.

## Abstract

Many IoT(Internet of Things) systems run Android systems or Android-like systems. With the continuous development of machine learning algorithms, the learning-based Android malware detection system for IoT devices has gradually increased. However, these learning-based detection models are often vulnerable to adversarial samples. An automated testing framework is needed to help these learning-based malware detection systems for IoT devices perform security analysis. The current methods of generating adversarial samples mostly require training parameters of models and most of the methods are aimed at image data. To solve this problem, we propose a \textbf{t}esting framework for \textbf{l}earning-based \textbf{A}ndroid \textbf{m}alware \textbf{d}etection systems(TLAMD) for IoT Devices. The key challenge is how to construct a suitable fitness function to generate an effective adversarial sample without affecting the features of the application. By introducing genetic algorithms and some technical improvements, our test framework can generate adversarial samples for the IoT Android Application with a success rate of nearly 100\% and can perform black-box testing on the system.