The rising increase of malicious software poses a threat of an immense nature, whereas the reciprocating of data is not limited to personal daily transactions, but dwelled deeply within large enterprises and organizations. The purpose of this project is to achieve a new approach in detecting mimicry malware that disguises itself to resemble a valid software to bypass the conventional antiviruses which are mainly signature-based anti-viruses. The proposed antivirus would follow a dynamic analysis interpretation of detecting malicious software using machine learning techniques, thus evolving and adapting to the ever-changing process of formation of malware.

Detecting Malware using a dynamic analysis approach.

Building a deep learning model that classifies mimicry malware.

Building a software that is able to sniff the multiple variants of a malware.

Delivering an endpoint protection software product that falls under the category of next generation anti-viruses.

The system will implement malware analysis through a dynamic approach rather the traditional static approach used in most antivirus programs. API call sequences which are a set of functions and data structures that a program can use to ask the operating system to do some functionality of the selected program will be used as the dataset along with NLP techniques such as TF-IDF and word embedding then processing using swarm intelligence algorithms specifically (Ant-Colony Optimization) and accordingly classification using deep learning to identify mimicry malware.