Abstract: Photo sharing is an attractive feature in Online Social Networks (OSNs) but it may leak users privacy if they are allowed to post, comment, and tag a photo freely. This issue of sharing the photos of individual or himself/herself is addressed by the proposed scheme. The proposed scheme is used to prevent possible privacy leakage of a photo. For this purpose, an efficient facial recognition (FR) system is required that can recognize everyone in the photo. However, to train the FR system, more demanding privacy setting may limit the number of the photos that are publicly available. To solve this problem, the proposed scheme attempts to utilize users private photos by designing a personalized FR system and also provide security while posting the photo. A distributed consensus based method is also developed to reduce the computational complexity and protect the private training set. The efficiency of proposed scheme is calculated by using recognition ratio. The proposed mechanism is implemented as a proof of concept on Android application in OSNís (Online Social Networks) on Facebook platform.

Keywords: social networks, photo privacy.