Anti-collusion Fingerprinting for Multimedia
Digital fingerprinting is a technique for identifying
users who use multimedia content for unintended purposes, such
as redistribution.These are embedded into the content using watermarking techniques that are designed to be robust to a variety of attacks. the problem
of designing fingerprints that can withstand collusion and allow
for the identification of colluders is discussed in this article. collusion problem for additive embedding is described , then the
effect that averaging collusion has on orthogonal modulation is studied. We next
develop a fingerprinting scheme based on code modulation that
does not require as many basis signals as orthogonal modulation. anti-collusion codes
(ACCs) is proposed which have the property that the composition of any
subset of K or fewer codevectors is unique. Due to this property groups of K or fewer colluders can be identified.

FINGERPRINTING AND COLLUSION:
additive embedding is a technique where a watermark signal is added to a host signal.One important application of fingerprinting is identifying a
user who is redistributing marked content by detecting the
watermark associated with the user to whom it was sold. the content owner may be able to more closely
monitor future actions of that user or gather evidence supporting
that userâ„¢s illicit usage of the content.

ORTHOGONAL MODULATION AND ANTICOLLUSION:
methods of orthogonal
modulation for embedding unique fingerprints in multiple
copies of images is discussed here.the effect of collusion on orthogonal modulation can be studied
by calculating the distance between the constellation
points and averages of the constellation points drawback for using orthogonal modulation
in data embedding is the large number of orthogonal signals
needed to convey a specific number of bits.


http://ece.umd.edu/~minwu/public_paper/J...al_TSP.pdf