为高分辨率生成图像设计不可见且抗干扰的水印技术
InvisMark: Invisible and Robust Watermarking for AI-generated Image Provenance
- 用先进神经网络嵌入难以察觉的水印
- 在各种操作下仍保持97%以上水印准确率
- 可嵌入256位水印，适合真实场景溯源
AI生成图像的泛滥加剧了内容认证的需求。本文提出InvisMark，一种专为高分辨率生成图像设计的新水印技术。该方法利用先进的神经网络架构与训练策略，嵌入难以察觉但极具鲁棒性的水印。InvisMark在不可察觉性上表现优异（PSNR≈51，SSIM≈0.998），同时在多种图像操作下仍保持超过97%的比特准确率。我们成功编码了256位水印，显著提升承载容量，结合纠错码可嵌入带有校验的UUID，即使在严重失真下也能实现近乎完美的解码。此外，针对潜在攻击漏洞提出应对策略。通过高不可察觉性、大容量和强抗篡改能力，InvisMark为复杂生成内容的来源验证提供了坚实基础。源代码已开源：https://github.com/microsoft/InvisMark。
原文摘要 · Abstract (English)
The proliferation of AI-generated images has intensified the need for robust content authentication methods. We present InvisMark, a novel watermarking technique designed for high-resolution AI-generated images. Our approach leverages advanced neural network architectures and training strategies to embed imperceptible yet highly robust watermarks. InvisMark achieves state-of-the-art performance in imperceptibility (PSNR$\sim$51, SSIM $\sim$ 0.998) while maintaining over 97\% bit accuracy across various image manipulations. Notably, we demonstrate the successful encoding of 256-bit watermarks, significantly expanding payload capacity while preserving image quality. This enables the embedding of UUIDs with error correction codes, achieving near-perfect decoding success rates even under challenging image distortions. We also address potential vulnerabilities against advanced attacks and propose mitigation strategies. By combining high imperceptibility, extended payload capacity, and resilience to manipulations, InvisMark provides a robust foundation for ensuring media provenance in an era of increasingly sophisticated AI-generated content. Source code of this paper is available at: https://github.com/microsoft/InvisMark.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。