English(EN) DRIFT: Removing Diffusion Watermarks by Deflecting the Generative Trajectory

新的DRIFT攻击可移除AI图像的扩散水印

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-08 03:54

研究人员开发了DRIFT，一种能够从生成图像中移除扩散水印的新型黑盒攻击方法。该方法结合了部分前向扩散和随机反向重采样，以模糊生成轨迹，使得水印难以恢复。DRIFT在不要求密钥或梯度优化的前提下，在各种水印方案中实现了98-100%的攻击成功率，同时保持了高质量的图像。 AI

影响这项研究揭示了AI图像水印的一个漏洞，可能影响内容的真实性和版权执行。

排序理由详细介绍一种从AI生成图像中移除水印的新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 1 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍一种从AI生成图像中移除水印的新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 1 days old; Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

Hugging Face Daily Papers TIER_1 English(EN) · 2026-09-08 03:54

DRIFT：通过偏转生成轨迹来移除扩散水印

Diffusion watermarking embeds verifiable signals into the generative process and commonly verifies them by recovering trajectory-dependent evidence, making the marks robust to conventional pixel-space distortions. Existing removal attacks either regenerate along deterministic tra…