Traffic Pattern-Based mostly Content Leak Detection for Trustworthy Content Delivery Networks

Abstract

Due to the increasing quality of transmission streaming applications and services in recent years, the difficulty of sure video delivery to stop undesirable content-leakage has, indeed, become crucial. While conserving user privacy, typical systems have addressed this issue by proposing strategies supported the observation of streamed traffic throughout the network.These standard systems maintain a high detection accuracy whereas managing a number of the traffic variation within network delay and packet loss and their detection performance well degrades thanks to the many variation of video lengths.In this paper, we focus on the solution overcoming this issue by proposing a unique content-leakage detection theme that's strong to the variation of the video length.By comparison videos of various lengths, we tend to confirm a relation between the length of videos to be compared and also the similarity between the compared videos.Therefore, we tend to enhance the detection performance of the projected theme even in associate degree setting subjected to variation long of video.Through a experimentation and testing procedure , the potential of achieving of our projected theme is evaluated in terms of variation within the length of video , delay in qualities of video, and loss of packets.