Daniel Gibert, PhD

Daniel Gibert, PhD

Researcher at the Artificial Intelligence Research Institute (IIIA-CSIC)

Orthrus: A Bimodal Learning Architecture for Malware Classification

Published in International Joint Conference on Neural Networks (IJCNN), 2020

We introduce Orthrus, a bimodal approach for malware categorization based on deep learning. Orthrus combines two modalities of data:

  • The byte sequence representing the malware’s binary content
  • The assembly language instructions extracted from the assembly language source code of malware Orthrus performs automatic feature learning and classification with a convolutional neural network.

Recommended citation: Daniel Gibert, Carles Mateu, Jordi Planes. (2020). "Orthrus: A Bimodal Learning Architecture for Malware Classification." IJCNN 2020.
Download Paper