1 3 DOI 10.1007/s00530-014-0442-5 Multimedia Systems REGULAR PAPER Scene-based fingerprinting method for traitor tracing Sachin Mehta · Rajarathnam Nallusamy · Balakrishnan Prabhakaran Received: 6 June 2014 / Accepted: 26 November 2014 © Springer-Verlag Berlin Heidelberg 2014 collusion, scene dropping, scene addition, and other com- mon signal processing attacks. Keywords Traitor tracing · Watermarking · Fingerprinting · QR code 1 Introduction With the advancement in multimedia and network tech- nologies, new models for distribution of multimedia con- tent have emerged and are gaining popularity among the consumers. Distribution channels such as video-on-demand services pose new challenges to the security measures aimed at protecting the multimedia content from Intellec- tual Property Right (IPR) violations. Digital watermarking is a deterring measure which has been adopted to shield the multimedia content from IPR violations, allowing embed- ding of unique information inside each instance of the multimedia content to be distributed. Unique information, generally referred as fingerprint, is linked to the consumer of the multimedia content. When illegal copies of the mul- timedia content are found, the detection of unique informa- tion allows tracing back to the legal user who is involved in unauthorized or illegal usage of the content, also referred as traitor. Multimedia content distribution systems are based on server–client architecture. Watermark can be embedded either at client or network or server side [6, 18]. However, adoption of watermark technology is entirely governed by multimedia application requirements and is hard to find a ubiquitous solution covering wide spectrum of multimedia applications. To illustrate, client-based approaches can be used in broadcasting of multimedia content via set-top box where a hard link between hardware and software exists. On Abstract In this paper, scene-based fingerprinting method for traitor tracing is proposed which is compu- tationally less complex and handles large user group, say 10 11 users while requiring few frames to embed the water- mark. The proposed method uses QR code as a watermark due to its three main features: (1) inherent templates, (2) noise resiliency, and (3) compact size. The proposed method creates the QR code watermark on-the-fly which is then segmented and embedded parallely inside the scenes of video using the watermarking key. The features of QR code, segmentation, and watermarking key not only help the proposed method in supporting a large user group but also make it computationally fast. Further, synchroniza- tion issues may arise due to addition and deletion of scenes. To avoid such scenarios, the proposed method matches the inherent templates present in QR code with the templates present in the segments of the extracted watermark. Experi- mental results show that the proposed method is compu- tationally efficient and is robust against attacks such as Communicated by L. Zhou. This work was done when S. Mehta and R. Nallusamy were working with Infosys Labs, Infosys Limited, Bangalore 560100, India. S. Mehta (*) AMD India Pvt. Ltd., Bangalore 560066, India e-mail: sachin.mehta@amd.com R. Nallusamy Embnology Solutions Private Limited, Bangalore 560037, India e-mail: raja@embnology.com B. Prabhakaran Department of Computer Science, University of Texas at Dallas, Richardson, TX 75080, USA e-mail: bprabhakaran@utdallas.edu