IJARCCE International Journal of Advanced Research in Computer and Communication Engineering ISO 3297:2007 Certified  Impact Factor 7.39  Vol. 11, Issue 5, May 2022 DOI: 10.17148/IJARCCE.2022.115124 © IJARCCE This work is licensed under a Creative Commons Attribution 4.0 International License 692 ISSN (O) 2278-1021, ISSN (P) 2319-5940 Anti-Spoofing Based Secured Transaction Using Facial Recognition And 2FA Anukul Muley 1 , Akash Bendre 2 , Priti Maheshwari 3 , Shanmukh Kumbhar 4 , Prof. Bhagyashree Dhakulkar 5 1-4 Department of Computer Engineering, Dr. D. Y. Patil School of Engineering and Technology, Lohegaon, Maharashtra, India 5 Professor, Department of Computer Engineering, Dr. D. Y. Patil School of Engineering and Technology, Lohegaon, Maharashtra, India Abstract: People now-a-days utilize Automated Teller Machines (ATMs) in large numbers. People rely on ATMs to meet their daily demands in a convenient manner. As it is a crucial aspect, security is a must. ATMs are automated teller machines that allow clients to deposit or withdraw money from banks. It has been discovered that the frequency of crimes involving ATMs has increased, necessitating the need for improved ATM security. RFID technology, fingerprint, facial recognition, iris scan, OTP, reference number, random keypad, and other technologies are all utilized to ensure the security of ATM machines. In a standard ATM system, card and PIN numbers are required for authentication, which causes security issues like lost cards, stolen pin numbers, card cloning, shoulder surfing, fake keyboard, skimming, etc. This paper mainly focuses on the implementation of Anti spoofing based facial recognition for ATM system using liveness detection. Keywords: ATM, Liveness Detection, Facial Recognition, Landmark Detection, OTP. 1. INTRODUCTION Automated Teller Machines (ATMs) have enhanced a basic fact of our existence. It plays a vital act in our regular transactions. An ATM is an e-banking machine that admits clients to complete elementary transactions without going to the bank. Anyone with a credit card or debit card can get cash from an ATM at any time by following a few easy steps. The first ATMs came in 1967 on the street in Enfield, London at a branch of Barclays Bank, and immediately they have grown in number to over 2 million global. When the investment sector introduced ATMs the habit of credit and debit cards has raised during the whole of the world. Banks had decreased their foundation costs by presenting Automatic Teller Machine (ATM) and Internet websites by which the customer's transactions will carry out easily and in a smooth way. ATM is a digital machine mainly used for gaining approach to different banking services anywhere without the assist of any financial institution staff. The users prefer ATMs for all physical transaction purposes, like money withdrawal and money deposit without going to the bank. In ATMs, the user experience has become a critical component that banks must deliver. However, this might lead to an increase in robberies and attacks on ATMs and internet banking using a variety of fraudulent tactics. However, technical advancements in the financial sector provide better security against fraudulent activity. However, there are various technologies like RFID technology, fingerprint, face recognition, iris scan, OTP, reference number, random keypad, and other technologies that are utilised to ensure security for ATM machines. In a standard ATM system, Card and PIN numbers are used for authentication and security is a major problem, with issues such as lost cards, stolen pin numbers, card cloning, shoulder surfing, false keyboards, skimming, and eavesdropping etc. ATM skimming is a way of action payment card fraud in which the fraudsters try to ransack PINs and additional main facts by rigging machine accompanying secret record device. Card shimming is an attack that involves inserting a very tiny device containing a microprocessor and flash memory into a card reader or ATM to collect user data. The information obtained this way is subsequently sold on the Internet or used to clone magnetic strip cards. In an Eavesdropping attack, a small hole is being made in the ATM device or approach gained to the top box of the ATM device by which electronic links are then attached straightforwardly to the card reader that helps them to capture card and PIN details. These problems gave rise to biometric-based ATMs. As biometrics are unique for each consumer, further making the ATMs more impenetrable. We proposed a biometric system that uses a unique trait or characteristic enables automated authentication for any user to stop these frauds - card cloning, shoulder surfing, fake keyboard, skimming, etc.