Detecting Portable Executable Malware by Binary Code Using an Artificial Evolutionary Fuzzy LSTM Immune System

As the planet watches in shock evolution of COVID-19 pandemic, new forms sophisticated, versatile, and extremely difficult-to-detect malware expose society especially global economy. Machine learning techniques are posing an increasingly important role field identification analysis. However, due to complexity problem, training intelligent systems proves be insufficient recognizing advanced cyberthreats. The biggest challenge information security using machine methods is understand polymorphism metamorphism mechanisms used by developers how effectively address them. This work presents innovative Artificial Evolutionary Fuzzy LSTM Immune System which, a heuristic method that combines evolutionary intelligence, Long-Short-Term Memory (LSTM), fuzzy knowledge, able adequately protect modern system from Portable Executable Malware. main innovation technical implementation proposed approach fact can only trained raw bytes executable file determine if malicious. performance was tested on sophisticated dataset high complexity, which emerged after extensive research PE offered us realistic representation their operating states. accuracy developed model significantly supports validity method. final evaluation carried out with in-depth comparisons corresponding algorithms it has revealed superiority immune system.