Machine learning for computer security has enjoyed a number of recent successes, but these tools aren’t perfect, and sometimes a novel family is able to evade file-based detection. This blog walks you through a method to automatically extract discriminative features from the entry point of portable executable (PE) malware — in this case, malware binaries in the “Portable Executable” format used by Microsoft Windows.

https://www.crowdstrike.com/blog/convolutional-neural-networks-are-male-models-for-pe-malware/