Abstract:

In recent years, widely used hash algorithms such as MD5 and SHA-1 have been found to have varying degrees of security risks.The iterative structure of the SHA-2 algorithm is similar to that of SHA-1, making it vulnerable to attacks as well.Meanwhile, SHA-3 has a complex internal structure and low implementation efficiency.To address these issues, a keyed hash function was designed and implemented based on chaotic neural network and C-MD structure.The approach involved improving the Merkle-Damgard structure by proposing the chaotic neural network Merkle-Damgard (C-MD) structure.This structure can be used to design a hash function that can withstand attacks such as the middle attack, multiple collision attack, and second pre-image attack for long information.Besides, the chaotic neural network was used as the compression function to increase the complexity of the hash function and improve its collision resistance, while also enabling it to output multiple lengths.Moreover, a plaintext preprocessor was designed, which used the coupled image lattice to generate chaos sequence related to the length of the plaintext to fill the plaintext, thus enhancing the ability of the hash function to resist length expansion attacks.Simulation results demonstrate that the proposed hash function performs faster than SHA-2, SHA-3 and the same type of chaotic hash function proposed by Teh et al.It can resist second pre-image attack, multi-collision attack and differential attack, while also exhibiting better collision resistance and mapping uniformity.In addition, the proposed Hash function can output Hash values of different lengths, making it suitable for use in digital signature, key generation, Hash-based message authentication code, deterministic random bit generator, and other application fields.

Key words: hash function, chaotic neural network, C-MD structure, coupled mapping lattice