Expectation Maximization decoding of Tardos probabilistic fingerprinting code

摘要

This paper presents our recent works on multimedia fingerprinting, improving both the fingerprinting code and the watermarking scheme. Our first contribution focuses on deriving a better accusation process for the well known Tardos codes. It appears that Tardos orginal decoding is very conservative: its performances are guaranteed whatever the collusion strategy. Indeed, major improvements stem from the knowledge of the collusion strategy. Therefore, the first part of this paper investigates how it is possible to learn and adapt to the collusion strategy. Our solution is based on an iterative algorithm a la EM, where a better estimation of the collusion strategy yields a better tracing of the colluders, which in return yields a better estimation of the collusion strategy etc.rnThe second part of this paper focuses on the multimedia watermarking scheme. In a previous paper, we already used the 'Broken Arrows' technique as the watermarking layer for multimedia fingerprinting. However, a recent paper from A. Westfeld disclosed a flaw in this technique. We present here a counter-measure which blocks this security hole while preserving the robustness of the original technique.