Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{179641,
        author = {keerthana G and Shalini N and Rejeena M and Sandhiya S and Srinithi M},
        title = {Automatic Malware Detection Using Recurrent Neural Network with Long Short-Term Memory},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {8267-8273},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=179641},
        abstract = {Automated malware detection is a vital aspect of cybersecurity that aims to identify harmful software and safeguard computer systems against attacks. Artificial Intelligence (AI) has recently enabled systems to detect malware by learning from various information. Offering protection consists of limiting the dimensions of feature data, excluding redundant information, and using more appropriate techniques to capture how malware’s actions occur over time, as usual detection methods can reduce accuracy and increase required resources. The challenges are handled by processing the data, choosing the essential features, and classifying them. At the beginning of the training process, feature values are normalized using Min-Max normalization for more reliable results. Grey Wolf Optimizer (GWO) is applied to pick the significant features from the CIC-MalMem-2022 dataset, which helps the model achieve better results by selecting only the key features. The Recurrent Neural Network-Long Short-Term Memory (RNN-LSTM) is used in the last step to identify malware by considering its changing behavior pattern sequence over time. To show that the proposal is compelling, accuracy, precision, recall, and F1-score are applied, proving that it detects malware accurately with fewer false positives and does not overload the computer.},
        keywords = {malware detection, cybersecurity, attacks, AI, min-max normalization, GWO, RNN-LSTM},
        month = {May},
        }