• Dr. K. Satya Sandeep
• Jaladi Karuna Sri
• Thota Swetha
• Dasari Triveni
• Pulimi AmruthaLakshmi

Remaining a crucial difficulty in the constantly changing field of cybersecurity is the effective and reliable identification of malware. This research presents an improved malware detection framework that makes use of Gated Recurrent Units (GRUs) and Attention techniques. The model enhances the interpretability and accuracy of malware detection by dynamically focusing on the most pertinent elements of the input data through the integration of attention techniques. The identification of complex and obfuscated malware is made possible by the GRU component, which efficiently extracts temporal dependencies and patterns from the data. Our Attention-GRU based technique performs much better than standard methods in terms of processing speed and detection accuracy, while maintaining low false-positive rates, as shown by experimental evaluations on benchmark datasets. The proposed model is a viable solution for real-time cybersecurity applications because of its scalability and capacity to respond to new and evolving malware threats. This work demonstrates how adding attention mechanisms to GRUs might improve malware detection systems' resilience and effectiveness.

Cybersecurity, Pertinent, Obfuscation, Resilience, Temporal , Attention, Benchmark.

"ENHANCED MALWARE DETECTION USING ATTENTION GRU", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 10, page no.36-45, October-2024, Available :http://www.jetir.org/papers/JETIRGN06005.pdf

"ENHANCED MALWARE DETECTION USING ATTENTION GRU", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 10, page no. pp36-45, October-2024, Available at : http://www.jetir.org/papers/JETIRGN06005.pdf