One of the most common way of verification is ‘Face Recognition’ which can also be implemented for communication between machines and humans. In industries, corporate sectors, financial exchanges etc., face detection and recognition are used for the purpose of authentication. Another area of interest is the communication of information securely. In this paper, for face detection process Haar-classifiers are used which produces an accuracy of around 99.4% for still images and 98.6% for video recordings. Using two algorithms i.e. LBPH algorithm and Eigenfaces face recognition is done. The former produces a recognition accuracy of 99.39% for still images and 99.32% for video recordings and latter produces accuracies of 99.28% and 98.87% for the same. The paper also proposes a more secure modified AES, whose modification done by 43 variable S - Box generation out of which 9 S - Box return correct inverse S – Box with the help of variable irreducible polynomial in GF (2 ⁸ ) finite field. Thus every time using the variable irreducible polynomial in GF (2 ⁸ ) a new S- Box and inverse S-Box is generated which makes it difficult for the intruders to crack modified AES.