| _version_ | 1866902261581479936 |
|---|---|
| author | M.Dattatreya Goud |
| author_facet | M.Dattatreya Goud |
| contents | <p>With increasing numbers of people relying on smartphones, especially Android phones, it has become very easy for cybercriminals to target such systems with the hope of finding loopholes to exploit. Malware in the Android environment that can destroy the device, steal sensitive information, or interrupt services is a serious security risk. Signature-based detection, as the traditional method, cannot be of assistance as malware still mutates at unimaginably fast rates. Machine learning has thus been a promising means of malware detection and malware classification with the capacity to identify complex patterns and evolving threats. This project tries to design a high-tech Android malware detection system using machine learning models, i.e., the Extra Tree Classifier and Logistic Regression models. Using the TUNADROMD dataset and integrating backend and frontend technologies like Python, Flask, and upcoming web frameworks, the application would be quick and easy to use. Overall, the project enables enhanced mobile security against cybersecurity by a trusted suite of tools that shields consumers from producing malware attacks</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_15863110 |
| institution | Zenodo |
| language | eng |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Android Malware Detection Using Equilibrium Optimized Deep Learning-Based Pattern Recognition M.Dattatreya Goud Android Malware, Machine Learning ,Cybersecurity ,Extra Tree Classifier, Logistic Regression, Malware Detection. <p>With increasing numbers of people relying on smartphones, especially Android phones, it has become very easy for cybercriminals to target such systems with the hope of finding loopholes to exploit. Malware in the Android environment that can destroy the device, steal sensitive information, or interrupt services is a serious security risk. Signature-based detection, as the traditional method, cannot be of assistance as malware still mutates at unimaginably fast rates. Machine learning has thus been a promising means of malware detection and malware classification with the capacity to identify complex patterns and evolving threats. This project tries to design a high-tech Android malware detection system using machine learning models, i.e., the Extra Tree Classifier and Logistic Regression models. Using the TUNADROMD dataset and integrating backend and frontend technologies like Python, Flask, and upcoming web frameworks, the application would be quick and easy to use. Overall, the project enables enhanced mobile security against cybersecurity by a trusted suite of tools that shields consumers from producing malware attacks</p> |
| title | Android Malware Detection Using Equilibrium Optimized Deep Learning-Based Pattern Recognition |
| topic | Android Malware, Machine Learning ,Cybersecurity ,Extra Tree Classifier, Logistic Regression, Malware Detection. |
| url | https://doi.org/10.5281/zenodo.15863110 |