Intel-Microsoft joint project turns malware into images

Yash Aryan

May 11, 2020

Researchers from Intel and Microsoft have collaborated to study the use of deep learning for malware threat detection. In this study, the malware is first converted into grayscale images. Then, the textural and structural patterns of the images are used to classify them as harmless or malicious, as well as classify the threats into their respective threat families. This type of approach has been named 'Static Malware-as-Image Network Analysis' or, STAMINA. The STAMINA approach has achieved high accuracy in detecting malware with low false positives. The study was performed on a dataset od 2.2 million PE file hashes provided by Microsoft.

Abridged fromET CISO