We revisit watermarking techniques based on pre-trained deep networks, in the light of self-supervised approaches. We present a way to embed both marks and binary messages into their latent spaces, leveraging data augmentation at marking time. Our method can operate at any resolution and creates watermarks robust to a broad range of transformations (rotations, crops, JPEG, contrast, etc). It significantly outperforms the previous zero-bit methods, and its performance on multi-bit watermarking is on par with state-of-the-art encoder-decoder architectures trained end-to-end for watermarking. The code is available at github.com/facebookresearch/ssl_watermarking
FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent Space
University of California, Santa Cruz（加州大学圣克鲁兹分校）；The University of Hong Kong（香港大学）；University of Science and Technology of China（中国科学技术大学）；IEG, Tencent（腾讯IEG）；Fudan University（复旦大学）
An Efficient Watermarking Method for Latent Diffusion Models via Low-Rank Adaptation and Dynamic Loss Weighting
Xiamen Key Laboratory of Data Security and Blockchain Technology, Huaqiao University, Xiamen 361021, China（厦门数据安全与区块链技术重点实验室，华侨大学，厦门361021，中国）；Department of Information Engineering and Mathematics of the University of Siena, Italy（意大利锡耶纳大学信息工程与数学系）；Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen 518060, China（广东省智能信息处理重点实验室，深圳大学，深圳518060，中国）；Shenzhen Key Laboratory of Media Security, Shenzhen University, Shenzhen 518060, China（深圳媒体安全重点实验室，深圳大学，深圳518060，中国）；SZU-AFS Joint Innovation Center for AI Technology, Shenzhen University, Shenzhen 518060, China（深圳大学人工智能技术联合创新中心）
ALIEN: Analytic Latent Watermarking for Controllable Generation
Beijing Institute of Technology, Beijing, China（北京理工大学）；School of Information Engineering, Minzu University of China, Beijing, China（中国民族大学信息工程学院）；School of Computer Science, The University of Adelaide, Adelaide, Australia（阿德莱德大学计算机科学学院）
DeepForgeSeal: Latent Space-Driven Semi-Fragile Watermarking for Deepfake Detection Using Adversarial Reinforcement Learning
The Signal Processing, Artificial Intelligence and Vision Technologies (SAIVT), Queensland University of Technology, Australia（信号处理、人工智能与视觉技术研究所（SAIVT），昆士兰理工大学）
CSGuard: Toward Forgery-Resistant Watermarking in Diffusion Models via Compressed Sensing Constraint
University of Science and Technology of China（中国科学技术大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（人工智能研究所，合肥国家科学中心）；Lenovo Research（联想研究院）
TraceMark-LDM: Authenticatable Watermarking for Latent Diffusion Models via Binary-Guided Rearrangement
Hangzhou Dianzi University（杭州电子科技大学）；Nanchang University（南昌大学）；School of Computer Science and Technology, Harbin Institute of Technology（计算机科学与技术学院，哈尔滨工业大学）；School of Computing and Communications, Lancaster University（计算与通信学院，兰卡斯特大学）
LVMark: Robust Watermark for Latent Video Diffusion Models
Department of Artificial Intelligence, Korea University, Seoul 02841, Republic of Korea（人工智能系，韩国大学，首尔02841，大韩民国）；Google DeepMind, Mountain View, CA 94043, USA（谷歌DeepMind，山景城，加利福尼亚州94043，美国）
Learning Generalizable and Efficient Image Watermarking via Hierarchical Two-Stage Optimization
Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China（深圳先进研究院，电子科学与技术大学）；School of Computer Science and Technology, Tongji University（同济大学计算机科学与技术学院）
WMVLM: Evaluating Diffusion Model Image Watermarking via Vision-Language Models
University of Science and Technology of China（中国科学技术大学）；Anhui Province Key Laboratory of Digital Security（安徽省数字安全重点实验室）；National University of Singapore（新加坡国立大学）
TAG-WM: Tamper-Aware Generative Image Watermarking via Diffusion Inversion Sensitivity
Anhui Province Key Laboratory of Digital Security, University of Science and Technology of China（安徽省数字安全重点实验室，中国科学技术大学）；School of Computing, National University of Singapore（computing学院，新加坡国立大学）
SWA-LDM: Toward Stealthy Watermarks for Latent Diffusion Models
Software Engineering Institute, East China Normal University（华东师范大学软件工程学院）；School of Computer Science and Technology, Harbin Institute of Technology (Shen Zhen)（哈尔滨工业大学（深圳）计算机科学与技术学院）；College of Integrated Circuits, Zhejiang University（浙江大学集成电路学院）
School of Computer Science, Beijing Institute of Technology（北京理工大学计算机学院）；Artificial Intelligence Research Institute, Shenzhen MSU-BIT University（深圳北理莫斯科大学人工智能研究院）；School of Medical Technology, Beijing Institute of Technology（北京理工大学医学技术学院）；College of Electronics and Information Engineering, Shenzhen University（深圳大学电子与信息工程学院）；Department of Computer Science, Faculty of Electrical Engineering and Computer Science, Ningbo University（宁波大学电气工程与计算机科学学院计算机系）
Glasgow College, University of Electronic Science and Technology of China（电子科技大学格拉斯哥学院）；School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）；School of Foreign Languages, University of Electronic Science and Technology of China（电子科技大学外国语学院）
Bootstrap your own latent: A new approach to self-supervised Learning
DeepMind；Imperial College（帝国理工学院）
我们介绍Bootstrap Your Own Latent（BYOL），一种新的自监督图像表示学习方法。BYOL依赖于两个神经网络，称为在线网络和目标网络，它们相互作用并相互学习。从图像的增强视图，我们训练在线网络来预测同一图像在不同增强视图下的目标网络表示。同时，我们用在线网络的缓慢移动平均值更新目标网络。虽然最先进的方法依赖于负对，但BYOL在没有负对的情况下达到了新的技术水平。BYOL在ImageNet上使用ResNet-50架构的线性评估和更大ResNet的$79.6\%$达到了$74.3\%$ top-1分类精度。我们表明，BYOL在传输和半监督基准测试中的表现与当前最先进的技术相当或更好。我们的实现和预训练模型在GitHub上提供。
