Using Machine Learning to Quantify the Multimedia Risk Due to Fuzzing

• Published in: Multimedia tools and applications Vol. 81; no. 25; pp. 36685 - 36698
• Main Authors: Kashyap, Gautam Siddharth, Malik, Karan, Wazir, Samar, Khan, Rijwan
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.10.2022; Springer Nature B.V
• Subjects: 1219: Multimedia Security Based on Quantum Cryptography and Blockchain; Computer Communication Networks; Computer Science; Data Structures and Information Theory; Machine learning; Multimedia; Multimedia Information Systems; Security; Special Purpose and Application-Based Systems; Wireless communications; Multimedia; Random forest algorithm; XGBoost; Machine learning; Fuzzing; Cybersecurity; Vulnerability; Gradient boosting
• DOI: 10.1007/s11042-021-11558-9
• ISSN: 1380-7501

There have been considerable advancements in multimedia technologies over the past 5 years. It has been observed that state-of-the-art multimedia systems face three broad categories of challenges: (1) Dependency on continuous network connections, (2) Data-sharing applications & collaboration, and (3) Security issues. Among these, security vulnerability poses a major threat to modern multimedia systems. Therefore, it is imperative to carefully investigate the security issues that can endanger wireless and mobile communications. At present, multimedia security research mainly focuses on wireless traffic monitoring, wireless system attacks, and wireless and mobile security. In this paper, we have used the network attack-type, “ Reconnaissance ”, which contains two types of malicious activities: (1) OS scanning, and (2) Fuzzing. The goal of this paper is to quantify multimedia security risks due to Fuzzing by using various types of machine learning models. The highest accuracy i.e., 96.8%, is obtained using the XGBoost classifier, which is good compared to the existing models present in the literature. This is the first paper, to the best of our knowledge, that uses machine learning methods to differentiate between benign and malignant Fuzzing attacks.