🤖 AI Summary
This work proposes a deep steganographic framework supporting multiple users and multiple keys to address the limitations of existing methods—such as PUSNet—that only accommodate single-user, single-key scenarios and thus fail to ensure security isolation in multi-user settings. Building upon the original purification and steganography capabilities, the proposed approach introduces a mismatched-key isolation loss function to establish a rigorous key isolation mechanism. This design effectively prevents unauthorized keys from decoding secret messages and mitigates cross-key information leakage, while simultaneously preserving high visual quality of stego images and enabling accurate recovery of embedded secrets. Consequently, the method significantly enhances steganographic security in multi-user environments.
📝 Abstract
Steganography conceals secret information within innocuous carriers while preserving visual fidelity and enabling reliable recovery. Recent unified networks operate normally under untriggered conditions but switch to hidden steganographic tasks when triggered. PUSNet follows this paradigm by performing image purification during normal operation and steganographic embedding when activated. However, it supports only a single user with one key pair, limiting its applicability in multi-user settings. We propose PUSNet-MK, a multi-key extension that enforces strict key isolation via a mismatched-key isolation loss, effectively preventing cross-key decoding when a wrong key is applied. This design preserves the intended steganographic behavior while addressing a critical security limitation of PUSNet. Extensive experiments demonstrate that PUSNet-MK produces high-quality stego images and accurate secret recovery, while preventing unintended information leakage.