Image-Based Malware Classification on Noise Extraction

Any malicious software designed to cause harm or damage to a computer system can be termed as malware. One common form of malware is as executable files. Such files are often used as a delivery mechanism for malware since they can be easily disguised as legitimate software and can be executed without raising suspicion. They are often used to exploit vulnerabilities in software, allowing malware to bypass security measures and gain access to sensitive information. There are several methods used to detect malware in executable files, including Signaturebased detection, Behavioral-based detection, Heuristic-based detection, Sandboxing, Machine Learning and Artificial Intelligence (AI). It\u27s worth noting that even the best anti-malware software can\u27t detect all types of malware. Out of them, AI is considered better for detecting malware in executable files because it has the capability to learn and adapt to new threats. Identifying features such as code obfuscation and anti-debugging techniques can make malware detection easier for AI techniques. AI algorithms use machine learning to identify patterns and relationships in data that might be indicative of malware. These algorithms can learn from vast amounts of data and continuously improve their accuracy in detecting malware. Malware can be hidden in images to evade detection by traditional security measures and converting executable files to images is a common technique used by attackers to evade detection. By classifying malware in images, security systems can detect and prevent the spread of these threats, protecting organizations and individuals from potential harm. As a part of this project, we will see how we can use the noise data in malware images and how the presence and absence of such noise data affects the performance of Convolutional Neural Networks (CNN). We will also look at how obfuscation in images might result in the use of noise for malware classification