Practical estimators of the secret spreading vector for Improved Spread Spectrum modulations . Statistical analysis and results . ( internal report )

where 0 ≤ λ ≤ 1 is the host-rejection parameter, ν is a parameter for fixing the embedding distortion, and Mi ∈ {0, 1} is the binary message (equiprobable) embedded in Xi. The vector Xi denotes the host signal, whereas s0 is the secret spreading vector, both of dimension n. The classical additive spread spectrum modulation (add-SS) is a particular case of (1) for λ = 0. In our statistical model, we assume that the host is i.i.d. Gaussian, i.e. Xi ∼ N (0, σ2 XIn) , i = 1, . . . , No. In the following, the spreading vector is assumed to be of unit norm. Under this assumption, the embedding distortion per dimension results in