摘要：The MD5, proposed by R. Riverst in 1992, is a widely used hash function with Merkle-Damgard structure. In the literature, many studies have been devoted to classical cryptanalysis on the MD5, such as the collision attack, the preimage attack etc. In this paper, we propose a new differential fault analysis on the MD5 compression function in the word-oriented random fault model. The simulating experimental results show that 144 random faults on average are required to obtain the current input message block. Our method not only increases the efficiency of fault injection, but also decreases the number of fault hash values. It provides a new reference for the security analysis of the same structure of the hash compression functions.
