A Probabilistic Error-Correcting Scheme
S. Decatur, O. Goldreich, D. Ron
Abstract: In the course of research in Computational Learning Theory, we found ourselves in need of an error-correcting encoding scheme for which few bits in the codeword yield no information about the plain message. Being unaware of a previous solution, we came-up with the scheme presented here. Since this scheme may be of interest to people working in Cryptography, we thought it may be worthwhile to ``publish'' this part of our work within the Cryptography community. Clearly, a scheme as described above cannot be deterministic. Thus, we introduce a probabilistic coding scheme which, in addition to the standard coding theoretic requirements, has the feature that any constant fraction of the bits in the (randomized) codeword yields no information about the message being encoded. This coding scheme is also used to obtain efficient constructions for the Wire-Tap Channel Problem.
Keywords: Error Correcting Codes, Privacy, Wire-Tap Channel, Computational Learning Theory.
comment: received April 21st, 1997. Revised June 25th, 1997.
contact author: oded@theory.lcs.mit.edu
Fetch PostScript file of