The face is an important feature of the human body for identifying persons in large crowds. Since then, it has been the most widely used and recognized biometric technique due to its distinctiveness and inclusivity. Facial recognition biometrics is now often employed. In addition to recognizing faces, a face recognition system should be able to recognize efforts at face spoofing using digital presentations or printed faces. Examining facial liveness, such as eye blinking and lip movement, is a genuine spoofing avoidance strategy. However, when it comes to video-based replay attacks, this strategy is useless. This research therefore suggests a CNN (Convolutional Neural Network) classifier in conjunction with face liveness detection. The blinking eye module, which assesses eye opening and lip movement, and the CCN classifier module are the two modules that make up the anti-spoofing technique. Our CNN classifier may be trained using a dataset from a number of publically accessible sources. According to the test results, the developed module is capable of identifying several types of facial spoof assaults, including those that use masks, posters, or smartphones.