发表机构
East China University of Science and Technology; University of Cambridge; University College London（华东理工大学; 剑桥大学; 伦敦大学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种新的图像隐写方法，将8位消息嵌入2D高斯表示参数中，通过密钥选择微调子集，在保持高视觉质量的同时实现可靠解码，并验证了在不同参数类型和简化设置下的鲁棒性。
AI 中文摘要
基于2D高斯的图像表示正变得越来越流行，我们的工作提出了一种新的隐写术方法，将信息嵌入到高斯参数中，而非图像像素中。我们首先将该表示的参数拟合到目标图像上，并使用秘密密钥选择这些参数的一个子集进行微调，从而在保持重建图像高视觉保真度的同时嵌入一个8位消息。在三个合成图像上的三十次拟合实验表明，正确的密钥可以无错误地恢复消息，而使用错误密钥解码时，比特错误率（BER）为0.543，接近随机猜测。与使用密钥的随机选择相比，选择干扰最小的编辑能更可靠地恢复消息（单侧p=0.031），且视觉质量的平均PSNR代价仅为0.091 dB。该嵌入方法可迁移到112张256×256的自然图像上，使用4096个高斯。正确密钥的BER为0.000，而错误密钥下的解码仍接近随机猜测，为0.520。我们的方法通过三种高斯参数类型嵌入载荷：对数各向异性、不透明度和颜色亮度。在另一个九次拟合的简化设置中，移除了颜色亮度，因此载荷使用两种而非三种参数类型，减少了33.3%；所有256个高斯仍保留在拟合表示中。正确的密钥仍能无错误地恢复消息。然而，错误密钥的BER从0.514上升到0.571，离随机猜测（0.5）更远。
英文摘要
2D Gaussian-based image representation is becoming increasingly popular, and our work proposes a new approach to steganography by embedding information within Gaussian parameters rather than image pixels. We first fit the parameters of this representation to the target image and employ a secret key to select a subset of these parameters for fine-tuning, allowing us to embed an 8-bit message while maintaining high visual fidelity in the reconstructed image. Thirty fitting experiments on three synthetic images show that the correct key can recover the message without error, while decoding with incorrect keys yields a Bit Error Rate (BER) of $0.543$, close to random guessing. Compared with random selection using the key, selecting the least-disturbing edits recovers the message more reliably (one-sided $p=0.031$), and the average PSNR cost is only $0.091$ dB in visual quality. The embedding method transfers to 112 natural images at $256\times256$ using 4,096 Gaussians. The correct-key BER is $0.000$, and decoding under a wrong key stays close to random guessing at $0.520$. Our method embeds the payload through three Gaussian parameter types: log-anisotropy, opacity, and color luminance. In a separate nine-fit reduced setting, color luminance is removed, so the payload uses two instead of three parameter types, a $33.3\%$ reduction; all 256 Gaussians remain in the fitted representation. The correct key still recovers the message without error. However, wrong-key BER rises from $0.514$ to $0.571$, moving farther from random guessing ($0.5$).
Comments4 pages, 2 figures, 3 tables; 2-page supplementary material in ancillary files. Accepted to SIGGRAPH Asia 2026 Technical Communications
