Image-based APK malware classification

This service converts an input APK to an Image, and tries to classify it using a pre-trained Convolutional Neural Network, trained on image-based malware classification. The conversion is made by reading the bytes sequences of the APK, and cast them to grayscale pixels. The service is in Beta Version, and can classifying the following malware families: ['Airpush' 'Dowgin' 'FakeInst' 'Fusob' 'Jisut' 'Mecor'].

The result after classification of your APK file is:

Error: File not allowed

Error: Server not found


DroidDefender is a proof-of-concept, an Android antimalware specifically designed and developed to detect zero-day malware. DroidDefender is based on representing an Android application as an image and employs a deep learning model.

Disclaimer ▾