Research on Copyright Protection Method of Big Data Based on Nash Equilibrium and Constraint Optimization
Bin Shi, YabinXu · Proceedings of the ACM Turing Celebration Conference - China · 2020
Data watermarking technology is an effective means to protect the copyright of big data. In order to embed robust and highly available data watermarks, firstly, based on the game theory, a Nash equilibrium model between watermark robustness and data quality is established to solve the optimal number of data partitioning. Then, the mapping relationship between data partitioning and watermark bit is established by using secure hash algorithm. Finally, under the constraint of data usability, the improved particle swarm optimization algorithm is used to calculate the optimal solution of data change for each data partitioning, and then the data is changed accordingly to complete the embedding of watermark bit. In order to verify the copyright ownership of big data, this paper also gives the corresponding watermark extraction method. Watermark extraction is the inverse process of watermark embedding. First, traverse all partitions and extract the possible embedded bit values in each data partitioning. Then, the actual embedded watermark bit is finally determined by majority voting strategies. The experimental results show that our proposed method can not only detect watermarks under different attack conditions, ensure the robustness of big data watermarks, but also achieve better data quality, and the comprehensive effect of data watermarks is better than the existing methods.