Generating, using artificial intelligence, test data to test malware scanner(s)

Abstract

In some cases, a server injects malicious code into a legitimate software package to create an injected package. The server uses an artificial intelligence to extract a plurality of parts of the injected package. The artificial intelligence mutates individual parts of the plurality of parts to create multiple mutated parts and assembles at least a portion of the multiple mutated parts to create a mutated malware. A malware scanner is used to determine a risk score associated with the mutated malware. When the score satisfies a predetermined threshold, the mutated malware is stored in a set of mutated malware. After determining that a number of mutated malware in the set of mutated malware satisfies a requested number, the malware scanner is modified to increase an accuracy of detecting the malicious code.