KIStego: Key-Independent Secure Image Distribution via Bipartite Structural Invariants

Generative Image Steganography (GIS) embeds complex secrets within stego-images that are indistinguishable from the stochastic synthesis process itself. It achieves this by exploiting the reversible probability flow between Gaussian noise and the natural image manifold. However, existing steganography faces a key-dependency paradox: precise secret extraction usually requires an external private key or random seed to synchronize the denoising path. In this paper, we present KIStego, a training-free framework substituting cryptographic secrecy with structural redundancy for Key-Independent, high-resolution secure distribution. Our dual-guidance mechanism utilizes structural latent guidance to project secrets into a bipartite manifold via downsampling and halftoning, yielding self-synchronizing shares. Measurement posterior sampling leverages these shares as discrete invariants to steer a differentiable restoration. By backpropagating through a differentiable measurement surrogate, KIStego reconstructs high-fidelity continuous-tone details from sparse binary observations, mitigating fidelity loss from inversion drift. KIStego offers an endogenous secure image distribution paradigm by connecting discrete structural invariants with high-fidelity generative reconstruction.

Hiding private, sensitive images inside realistic AI-generated pictures offers a powerful way to protect data privacy online. However, traditional techniques require both parties to securely share a secret key beforehand—if that key is lost, stolen, or corrupted, the hidden image cannot be recovered. To solve this, we introduce KIStego, a framework that eliminates the need for pre-shared keys. Instead of using a password, KIStego splits a sensitive image into two scrambled, innocuous fragments, each embedded into a separate AI-generated picture. When the receiver collects both images, the mathematical relationship between the fragments automatically reconstructs the original. By removing the need for external keys, KIStego provides a more secure and practical solution for sharing confidential visual data over untrusted networks.