DiffStega:面向通用免训练无载体图像隐写的扩散模型方法
DiffStega: Towards Universal Training-Free Coverless Image Steganography with Diffusion Models
AI总结:
针对现有扩散模型驱动的无载体图像隐写存在的提示词易泄露、安全性不足等问题,提出免训练的DiffStega策略,结合密码依赖的图像提示词与Noise Flip技术,在通用性、密码敏感性和恢复质量上均优于现有方法。
摘要:
传统图像隐写专注于将一幅图像隐藏在另一幅图像中,旨在规避未授权实体的隐写分析。无载体图像隐写(Coverless Image Steganography, CIS)通过不使用任何载体图像提升了隐蔽性。近期研究借助扩散模型,将文本提示词作为 CIS 中的密钥使用。然而,该方法面临三大挑战:私有提示词被猜中时方法失效、需构建具备语义多样性的公共提示词、频繁传输过程中存在提示词泄露风险。为解决这些问题,我们提出 DiffStega,一种创新的、基于扩散模型的免训练通用 CIS 策略。DiffStega 使用依赖密码的参考图像作为图像提示词,与文本提示词配合使用,确保仅授权方能够提取隐藏信息。此外,我们开发了 Noise Flip(噪声翻转)技术,进一步增强隐写的安全性以抵御未授权解密。为在通用 CIS 任务中全面评估我们的方法,我们构建了一个包含多种图像隐写实例的数据集。实验表明,我们的方法相较现有方法有显著提升,尤其在通用性、密码敏感性和恢复质量方面。代码可在 https://github.com/evtricks/DiffStega 获取。
英文摘要:
Traditional image steganography focuses on concealing one image within another, aiming to avoid steganalysis by unauthorized entities. Coverless image steganography (CIS) enhances imperceptibility by not using any cover image. Recent works have utilized text prompts as keys in CIS through diffusion models. However, this approach faces three challenges: invalidated when private prompt is guessed, crafting public prompts for semantic diversity, and the risk of prompt leakage during frequent transmission. To address these issues, we propose DiffStega, an innovative training-free diffusion-based CIS strategy for universal application. DiffStega uses a password-dependent reference image as an image prompt alongside the text, ensuring that only authorized parties can retrieve the hidden information. Furthermore, we develop Noise Flip technique to further secure the steganography against unauthorized decryption. To comprehensively assess our method across general CIS tasks, we create a dataset comprising various image steganography instances. Experiments indicate substantial improvements in our method over existing ones, particularly in aspects of versatility, password sensitivity, and recovery quality. Codes are available at \url{https://github.com/evtricks/DiffStega}.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。