• Pyla Indira
• Mr. N Mahendra
• Dr. Chukkala Visweswara Rao

Contemporary malware employs modern techniques including polymorphism and metamorphism which makes it harder to be detected. Consequently, traditional methods which are solely reliant on signature-based systems are inefficient against such threats. The Apocalypse is Last project investigates the use of classical machine learning (ML) algorithms and deep learning (DL) architectures such as CNN and LSTM in malware detection. We employ grayscale images of malware samples in order to improve the detection of ‘zero-day’ attacks. The approach proposed omits the necessity of exhaustive feature engineering whilst achieving good precision and recall. Both public and private datasets were used in order to maintain strong and unbiased validation. Using both ML and DL, the system is able to meet such requirements as scaling, accuracy, and flexibility, thus presenting a particular scheme for malware detection and classification in the sphere of cyber security.

CNN, LSTM, malware

"ADAPTIVE MALWARE DETECTION FRAMEWORK USING MACHINE AND DEEP LEARNING MODELS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 1, page no.b213-b219, January-2025, Available :http://www.jetir.org/papers/JETIR2501149.pdf

"ADAPTIVE MALWARE DETECTION FRAMEWORK USING MACHINE AND DEEP LEARNING MODELS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 1, page no. ppb213-b219, January-2025, Available at : http://www.jetir.org/papers/JETIR2501149.pdf