We introduce a novel method for secure computation of biometric hash on dynamic hand signatures using BioPhasor mixing and 2 N discretization. The use of BioPhasor as the mixing process provides a one-way transformation that precludes exact recovery of the biometric vector from compromised hashes and stolen tokens. In addition, our user-specific 2 N discretization acts both as an error correction step as well as a real-to-binary space converter. We also propose a new method of extracting compressed representation of dynamic hand signatures using discrete wavelet transform (DWT) and discrete fourier transform (DFT). Without the conventional use of dynamic time warping, the proposed method avoids storage of user's hand signature template. This is an important consideration for protecting the privacy of the biometric owner. Our results show that the proposed method could produce stable and distinguishable bit strings with equal error rates (EERs) of 0 % and 9.4 % for random and skilled forgeries for stolen token (worst case) scenario, and 0 % for both forgeries in the genuine token (optimal) scenario.