Strength and Limitations of Publicly Available Anti-Malware Tools Against Obfuscated Malware
Kiran Aswal, Heman Pathak, Nipur Singh, Neena Gupta · 2023
Many industries, including the automobile industry, have seen inventive development in various application areas as a result of the Internet revolution. Autonomous vehicles aren't science fiction anymore; they are a reality. The transformation of existing Vehicular Networks (VANETs) into the Internet of Vehicles (IoV) resulted in numerous advantages, including im-proved traffic management and a safer driving experience. In the past, there have been reports of VANET cyberattacks involving vehicles that are not entirely autonomous. These attacks, however, are equally viable in a VANET with fully autonomous vehicles. Currently, available anti-virus tools are highly sophisticated, but malware writers are commonly one step ahead of the soft-ware, and new obfuscated viruses that current anti-virus software cannot recognize are constantly released. As a result, before adopting currently available anti-malware tools as a malware detection system in the Vehicular networks, it is necessary to evaluate their effectiveness against advanced malware. This research work investigates and presents the effectiveness of 72 publicly available anti-virus engines against 300 live malicious android applications and 70 benign applications. The experiment is conducted on Ubuntu 20.04, Intel i7 machine with 16 GB of memory to scan the malicious samples as well as benign samples from their respective local repositories through 72 anti-virus engines. A script is developed in python 3.5, which uses VirusTotal API to upload the malicious as well as benign samples to VirsuTotal and fetch the scanning report to our local log file. The results presented in the study show that majority of the malicious samples could not be detected. Out of 72 AV scanners considered in the study, the detection accuracy of only 5 scanners is in the range of 10% to the highest detection accuracy of 30.67 %, whereas the detection accuracy of the rest of the 67 AV scanners is below 6 %. Based on the literature review and experimental results derived in the study, the authors conclude that most of the known anti-virus tools can detect all known malwares but are in-efficient against highly dynamic, evolving, obfuscated mal wares and zero-day attacks.