A Novel Ransomware Virus Detection Technique using Machine and Deep Learning Methods
A. Charmilisri, Ineni Harshi, V Madhushalini, Laxmi Raja · 2023
Malware is typically found only after the victim gets a ransom demand. Ransomware detection systems detect the threat more quickly, allowing victims to take action before irreversible damage occurs. The identification of ransomware will assist in avoiding the loss of crucial data. After an intrusion, many users never access their original data again. Data will be lost permanently if a recent backup is not created. Endpoint detection is one of the virus-defense techniques that can stop malware as soon as an attacker gains access. Hence, the sensitive data can be kept safe by protecting the data. This study proposes a system for detecting ransomware attacks that uses machine learning and deep learning approaches to analyse the malware that enters the network in order to stop these malware attacks. Each file was initially analysed and examined in a computer system to see whether it’s vulnerable to attack. When there is network communication, each and every packet is detected. The assessed packets will be checked to see whether there was any unusual behaviour in the system’s activities. The goal of this study is to determine when a harmful signal first arises and where it happens in a ransomware workflow, as well as to allow early identification and stop ransomware activities before they cause significant damage.