One of the challenging issues in detecting malware is that modern stealthy obfuscated malware is a sophisticated type of malicious software that hides its actual goal and avoids detection by typical security systems. This form of malware uses a variety of obfuscation techniques to conceal its code, making it difficult for security researchers and antivirus technologies to detect its harmful activity. Understanding the complexities of obfuscated malware is critical for creating effective security measures to identify, analyze, and mitigate its effects on computer systems and networks. Inspired by those issues, this paper presents an efficient detection technique using memory feature extractors and machine learning classification techniques including Decision Tree (DT), Logistic Regression (LR), and Support Vector Machine (SVM). According to the findings, the suggested method may identify malware that has been concealed and obfuscated utilizing memory features, with an accuracy and F1-Score of 99.9%. Furthermore, this paper highlights the crucial research activity to employ advanced detection techniques as the cyber security landscape evolves, constant research and collaboration are critical for staying ahead of obfuscated malware.