In this paper, we propose, implement, and analyze the structures of two keyed hashfunctions using the Chaotic Neural Network (CNN). These structures are based on Spongeconstruction, and they produce two variants of hash value lengths, i.e., 256 and 512 bits. The firststructure is composed of two-layered CNN, while the second one is formed by one-layered CNN anda combination of nonlinear functions. Indeed, the proposed structures employ two strong nonlinearsystems, precisely a chaotic system and a neural network system. In addition, the proposed study isa new methodology of combining chaotic neural networks and Sponge construction that is provedsecure against known attacks. The performance of the two proposed structures is analyzed in termsof security and speed. For the security measures, the number of hits of the two proposed structuresdoesn’t exceed 2 for 256-bit hash values and does not exceed 3 for 512-bit hash values. In terms ofspeed, the average number of cycles to hash one data byte (NCpB) is equal to 50.30 for Structure 1,and 21.21 and 24.56 for Structure 2 with 8 and 24 rounds, respectively. In addition, the performance ofthe two proposed structures is compared with that of the standard hash functions SHA-3, SHA-2, andwith other classical chaos-based hash functions in the literature. The results of cryptanalytic analysisand the statistical tests highlight the robustness of the proposed keyed hash functions. It also showsthe suitability of the proposed hash functions for the application such as Message Authentication,Data Integrity, Digital Signature, and Authenticated Encryption with Associated Data.