CISC: Cognitively Imperceptible Generative Image Steganography with Security and Controllability
Authors:
- Yaxin ZengYZYaxin Zeng
- Jinhong ZhangJZJinhong Zhang
- Wei ZhouWZWei Zhou
- Ping WeiPWPing Wei
- Yunyun DongYDYunyun Dong
Preprint
- 6 February 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
Steganography aims to conceal secret information within ordinary media, providing an alternative to traditional encryption methods that may attract the attention of eavesdroppers. In recent years, cross-modal and generative steganography have leveraged multimodal data and diffusion models to enhance imperceptibility. However, existing approaches often provide limited controllability over generated content and may introduce security concerns when images and texts are transmitted simultaneously, as the accompanying text can potentially be exploited to facilitate message recovery.To address these challenges, we propose \textbf{CISC}: \textbf{C}ognitively \textbf{I}mperceptible Generative Image Steganography with \textbf{S}ecurity and \textbf{C}ontrollability. CISC incorporates two main designs: a mapping-sampling strategy and a dual-layer text transformation mechanism. The mapping-sampling strategy allows stego image generation to be guided by user-specified prompts, supporting flexible manipulation of visual content. Meanwhile, the dual-layer text transformation mechanism aims to reduce prompt-level information exposure during multimodal transmission.Experimental results show that CISC can generate controllable stego images while maintaining visual inconspicuousness, and it provides competitive performance in robustness and security-related evaluations, suggesting a practical pathway toward cognitively imperceptible and secure multimodal steganography.Keywords
This publication has 19 references indexed in Scilit:
- AeroVeil-FL: Privacy-preserving federated learning framework for UAV-assisted real-time disaster detectionComputers and Electrical Engineering, 2025
- Optimal frame selection-based watermarking using a meta-heuristic algorithm for securing video contentComputers and Electrical Engineering, 2024
- Anti-Rounding Image Steganography With Separable Fine-Tuned NetworkIEEE Transactions on Circuits and Systems for Video Technology, 2023
- Cross-Modal Text Steganography Against Synonym Substitution-Based Text AttackIEEE Signal Processing Letters, 2023
- JPEG Steganography With Content Similarity EvaluationIEEE Transactions on Cybernetics, 2022
- A Novel Image Steganography Method via Deep Convolutional Generative Adversarial NetworksIEEE Access, 2018
- Structural Design of Convolutional Neural Networks for SteganalysisIEEE Signal Processing Letters, 2016
- An Introduction to Image Steganography Techniques2012
- Image steganography method based on PVD and modulus function2011
- Using High-Dimensional Image Models to Perform Highly Undetectable Steganography2010