• Dr. R. G. Suresh Kumar
• Akshaya Ancy. P
• Gohila. S
• D. Swathi

The proposed system represents a significant leap forward in the ongoing battle against PDF malware, addressing a critical vulnerability inherent in existing approaches. This vulnerability lies in the susceptibility of current systems to evasive variants of PDF- based malware that can adeptly bypass machine learning-based classifiers. The proposed system offers a groundbreaking solution to combat PDF malware by leveraging the Long Short-Term Memory (LSTM) algorithm, addressing a critical vulnerability in existing approaches. Unlike conventional methods, our system integrates a pre-trained model, reducing training time while maintaining accuracy. This innovative approach tailored for detecting image-based malware within PDF files has shown remarkable performance improvements in rigorous comparative testing, surpassing current systems in accuracy and training efficiency. The integration of LSTM enhances the system's robustness, providing a proactive defense against the dynamic nature of PDF malware. Overall, our pioneering system not only enhances security measures against malicious PDF files but also introduces a more streamlined and responsive solution to combat the evolving tactics of digital threats. This advancement signifies a significant stride forward in cybersecurity, offering an effective defense against the continuously changing landscape of PDF-based malware threats.

Variational Autoencoder (VAE), PDF-based malware threats

"LEARNING APPROACH TO PDF MALWARE RECOGNITION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 7, page no.403-408, July-2018, Available :http://www.jetir.org/papers/JETIR1807A59.pdf

"LEARNING APPROACH TO PDF MALWARE RECOGNITION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 7, page no. pp403-408, July-2018, Available at : http://www.jetir.org/papers/JETIR1807A59.pdf