A Deep Learning Approach to the Malware Classification Problem using Autoencoders

• Dhiego Ramos Pinto Instituto Militar de Engenharia
• Julio Cesar Duarte Instituto Militar de Engenharia
• Ricardo Sant’Ana Instituto Militar de Engenharia

Resumo

Detecting malicious code or categorizing it among families has become an increasingly difficult task. Malware1 exploits vulnerabilities and employ sophisticated techniques to avoid their detection and further classification, challenging cybersecurity teams, governments, enterprises, and the ordinary user, causing uncountable losses annually.

Palavras-chave: Deep Learning, Machine Learning, Neural Networks, Unsupervised Pre-training, Autoencoder, Malware Classification, Static Analysis