Abstract:Revealing expressions of secret-key capacity (SKC) based on data sets from Gaussian MIMO channel probing are presented. It is shown that Maurer's upper and lower bounds on SKC coincide when the used data sets are produced from one-way channel probing. As channel coherence time increases, SKC in bits per probing channel use is always lower bounded by a positive value unless eavesdropper's observations are noiseless, which is unlike SKC solely based on reciprocal channels.
Abstract:This paper presents a study of continuous encryption functions (CEFs) of secret feature vectors for security over networks such as physical layer encryption for wireless communications and biometric template security for online Internet applications. CEFs are defined to include all prior continuous "one-way" functions. It is shown that dynamic random projection and index-of-max (IoM) hashing algorithm 1 are not hard to attack, IoM algorithm 2 is not as hard to attack as it was thought to be, and higher-order polynomials are easy to attack via substitution. Also presented is a new family of CEFs based on selected components of singular value decomposition (SVD) of a randomly modulated matrix of feature vector. Detailed empirical evidence suggests that SVD-CEF is hard to attack. Statistical analysis of SVD-CEF reveals its useful properties including its sensitivity to noise. The bit-error-rate performance of a quantized SVD-CEF is shown to exceed that of IoM algorithm 2.