Algorithmic Learning for Steganography: Proper Learning of k-term DNF Formulas from Positive Samples

摘要

Proper learning from positive samples is a basic ingredient for designing secure steganographic systems for unknown covertext channels. In addition, security requirements imply that the hypothesis should not contain false positives. We present such a learner for k-term DNF formulas for the uniform distribution and a generalization to q-bounded distributions. We briefly also describe how these results can be used to design a secure stegosystem.