Towards a privacy protection-capable noise fingerprinting for numerically aggregated data

Privacy protection and traitor tracing have always been two separate research subjects. Meanwhile, digital fingerprinting, which tracks illegally distributed media by creating a unique code for each user, has long regarded as one of the effective means tracking down illegal users. However, most existing fingerprinting schemes focus on how to design more robust or general fingerprint target users effectively, without paying attention privacy itself. Our paper proposes novel idea simultaneously perform massive aggregated data. And further, detailed Secure Noise FingerPrinting based Differential (SNFP-DP) scheme is proposed demonstrate feasibility integrating differential fingerprinting. The SNFP-DP builds well-designed noise specific computing node into numerically data set, realizing inserting disturbance in step. Noised Aggregated FingerPrint Data (NAFPD) generated our can be protected adding appropriate noise, while source dissemination determined identifying NAFPD. In addition, we instantiate real-world specifying values all key parameters. experimental results show that NAFPD meets requirements statistical analysis accuracy. it also robustness security characteristics Finally, conduct thorough performance through mathematical formula derivation attack simulation.