An Investigation of Quantum and Parallel Computing Effects on Malware Families Classification

Abstract

The proliferation of malicious software is a major concern for organizations and consumers alike. Malware is used to compromise computer systems and networks for malevolent purposes. Consequently, categorizing malware is essential for safeguarding systems from harmful assaults. Developers of malicious software are always coming up with novel techniques to avoid detection by security researchers. However, in recent years, quantum computing has developed rapidly and shown considerable advantages in a number of sectors, particularly in the area of cybersecurity. A quantum approach may be useful in conjunction with existing software for finding the most often occurring hashes and n-grams that are characteristic of malicious software. The time it takes to map n-grams to their hashes may be reduced if we load the table of hashes and n-grams into a quantum computer. The first step is to utilize Kilogram to identify the most prevalent hashes and n-grams in a large collection of malware. Once the hash table is generated, it is sent into a quantum simulator. The entangled key-value pairs are then searched through a quantum search method to locate the appropriate hash value. In contrast to the quantum algorithm's potential runtime of O(N) in the number of table lookups required to get the requisite hash values, re-computing hashes for a set of n-grams may take on average O(MN) time. The main purpose of this research is to address the significant effects of quantum and parallel computing on malware families’ classification.