Multimodal Information Steganography with Chaos-Gyrator Cascaded Encryption and Statistical Isolation

With the increasing diversity of multimedia data types, single-modal steganography is insufficient to meet the demand for the simultaneous covert communication of multiple types of data, and single optical transformation encryption schemes are insufficiently secure against cryptanalytic attacks. To address these challenges, this paper designs and implements a multimodal secret information steganography system based on the optical Gyrator transform. We propose a multimodal steganographic system for the covert transmission of three types of heterogeneous secret data—text, color images, and audio—using a three-level cascaded optical encryption architecture. The system first uniformly encapsulates the multimodal data into a unified bitstream via a Type–Length–Value (TLV) format; it then uses the Ushiki chaotic map to generate a pure phase mask for random phase modulation of the carrier image, followed by spatial-frequency scrambling via a fractional Fourier transform (FrFT, order γ = 1.6). The secret bitstream is embedded into all eight bit planes of the amplitude components in the FrFT domain using binary square representation, achieving an embedding capacity of 2.23 × 106 bits—approximately 8.5 times that of traditional LSB methods; finally, a speckle-noise-like ciphertext is output via a Gyrator transform (angle α = 0.5). Experiments demonstrate that under non-attack conditions, the system achieves lossless recovery with a zero bit-error rate. Under known-plaintext and chosen-plaintext attacks on the Gyrator layer, the PSNR of the recovered images was only 4.89 dB and 4.80 dB, respectively, and the secret information could not be effectively extracted, as the chaotic-FrFT pre-encryption statistically isolates the intermediate image from natural image statistics. This system provides a functionally complete and practically secure solution for multimodal covert communication.