• Velicheti Kavya
• Ramjee Maddula

The rapid evolution of malware poses a significant threat to digital ecosystems, affecting individuals, organizations, and national security. Traditional signature-based detection methods are increasingly ineffective against new and obfuscated malware variants. Our project presents a smart malware detection system built using machine learning to ensure both accuracy and efficiency. By analysing features extracted from executable files (such as APKs or PE files), the system classifies applications as malicious or benign. We utilize supervised learning algorithms—including Random Forest, Decision Trees, and Support Vector Machines—to train our model using labelled datasets. The model is optimized for accuracy, precision, recall, and low false-positive rates. Feature extraction and selection play a vital role in ensuring the robustness and efficiency of the detection system. The tool is designed with a simple, interactive interface that lets users upload files and instantly check them for malicious content. Our results demonstrate that ML models can outperform traditional methods in both detection speed and adaptability. The study emphasizes the importance of explain ability and region-based analysis in interpreting the results. We also identify practical gaps in deployment and the need for lightweight models for resource-constrained environments. This approach contributes to proactive cybersecurity defenses and paves the way for future AI-integrated malware prevention systems.

: Malware Detection, Machine Learning, Static Analysis, Random Forest, Cybersecurity, APK Analysis, Feature Extraction, Stream lit Interface, Executable Files, Classification Algorithm, Artificial Intelligence, Data Security, Threat Detection, Automation, Model Accuracy.

"Malware Detection Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 7, page no.g598-g604, July-2025, Available :http://www.jetir.org/papers/JETIR2507687.pdf

"Malware Detection Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 7, page no. ppg598-g604, July-2025, Available at : http://www.jetir.org/papers/JETIR2507687.pdf