信源平衡编码及其在流密码中的应用

Balanced Source Coding and Its Application in Stream Ciphers

本文对离散无记忆信源给出了一种编码方法,它使编码后信源输出有着最好的平衡性,即0与1的数目最大程度地接近。对等长编码,本文给出的方法是步优的;对基于Huffman码的平衡编码,在保持平均码长不变的情况下,本文给出的方法使0与1的平衡性达到最优。因为一般信源字符的频率是一个统计数字,这里的平衡性也是从统计角度来说的。最后我们还讨论了这种平衡编码对流密码中的非线性组合器在防止相关攻击方面的防护作用。

This paper gives a method of balanced coding for discrete memoryless sources such that the output sequence of the source has best balance,i.e.,the probabilities of the appearance of 0 and 1 are almost the same.For fixed-length coding,the method proposed in this paper is step-optimum.For balanced coding based on Huffman's code,by keeping the same average code word length,the method in this paper is optimum.Moreover,the application of balanced coding in stream Ciphers is also discussed.