• Omkar Hanumant Dalvi
• Shubham Sambhaji Veer
• Omkar Pandurang Babar
• Pratik Shivaji Babar
• Prof. Digamber Shelke

With increasing cases of ATM fraud and unauthorized access, this research presents an advanced security system incorporating Low Rank Representation Twin Tensor Kernel Deep Learning (LRR-TTK DL) and facial recognition. The proposed system integrates Deep Face-based authentication, Support Vector Machine (SVM) classification, and a shuffle keypad mechanism to enhance security. Additionally, an OTP verification module serves as a fallback measure. The architecture is designed to ensure robust authentication, fraud prevention, and user accessibility through a Tkinter-based graphical user interface (GUI) for both users and administrators. Experimental evaluation confirms the system's effectiveness in improving security measures for ATM transactions.

Component ,formatting, style ,styling ,insert.

"Advanced Security System for ATM Software with Facial Recognition and OTP with Shuffle Keypad Feature", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 4, page no.k778-k796, April-2025, Available :http://www.jetir.org/papers/JETIR2504A96.pdf

"Advanced Security System for ATM Software with Facial Recognition and OTP with Shuffle Keypad Feature", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 4, page no. ppk778-k796, April-2025, Available at : http://www.jetir.org/papers/JETIR2504A96.pdf