牛哥精选 · 一年

📋 全部 🤖 AI·大模型 ⚡ 效率工具 📝 深度技术 🚀 产品观察 💰 商业科技 🔓 开源项目 🎨 设计创意 📖 阅读推荐 🏷 资源合集 🌱 成长效率

📝 深度技术 arXiv 机器学习 2026-05-29

Echoes within the Reasoning: Stealthy and Effective Watermarking via Chain of Thought

利用思维链过程嵌入隐秘水印，为AI模型提供高效且不易察觉的版权保护新方法，已被ICML 2026接收。

arXiv:2605.28890v1 Announce Type: cross Abstract: Large Language Models with Chain-of-Thought reasoning capabilities represent valuable intellectual p…

思维链数字水印 ai安全 icml 推理过程

📝 深度技术 arXiv AI 2026-05-26

RAW: Robust Avatar Watermarking -- Benchmarking and Baseline

提出面向虚拟化身水印的鲁棒性基准与基线方法，填补了该领域系统评估的空白。

arXiv:2605.23994v1 Announce Type: cross Abstract: Digital avatar watermarking presents unique challenges: avatars are routinely post-processed with ba…

avatar水印鲁棒性水印基准测试基线方法数字水印

🤖 AI·大模型 TechCrunch 2026-05-20

OpenAI is making it easier to check if an image was made by their models

OpenAI联手Google用元数据和水印标记AI图片，一键验证真伪，杜绝造假。

OpenAI announced two new measures to help detect AI generated imagery: joining the open C2PA standard and adding Google's SynthID to its products.

openai 图片溯源 ai安全 synthid c2pa

📅 日期

2026-05-20 2026-05-19

🐂 牛哥精选

Echoes within the Reasoning: Stealthy and Effective Watermarking via Chain of Thought

RAW: Robust Avatar Watermarking -- Benchmarking and Baseline

OpenAI is making it easier to check if an image was made by their models

📅 日期