Android TV Malware Dataset

The smart TV ecosystem is rapidly expanding, allowing developers to publish their applications on TV markets to provide a wide array of services to TV users. However, this open nature can lead to significant cybersecurity concerns by bringing unauthorized access to home networks or leaking sensitive information. In this study, we focus on the security of Android TVs by developing a lightweight malware detection model specifically for these devices.We collected various Android TV applications from different markets and injected malicious payloads into benign applications to create Android TV malware, which is challenging to find in the market. We propose a machine-learning approach to detect malware and evaluate our model. Our findings indicate that the model performed well in rare malware cases on Android TVs.