Worst case attacks against binary probabilistic traitor tracing codes
Résumé
An insightful view into the design of traitor tracing codes should necessarily consider the worst case attacks that the colluders can lead. This paper takes an information-theoretic point of view where the worst case attack is defined as the collusion strategy minimizing the achievable rate of the traitor tracing code. Two different decoders are envisaged, the joint decoder and the simple decoder, as recently defined by P. Moulin \cite{Moulin08universal}. Several classes of colluders are defined with increasing power. The worst case attack is derived for each class and each decoder when applied to Tardos' codes and a probabilistic version of the Boneh-Shaw construction. This contextual study gives the real rates achievable by the binary probabilistic traitor tracing codes. Attacks usually considered in literature, such as majority or minority votes, are indeed largely suboptimal. This article also shows the utmost importance of the time-sharing concept in a probabilistic codes.