水印论文趋势 2023–2026

主要结论

• 水印论文从 2023 年的 6 篇增长到 2026 年的 56 篇，三年间扩大到约 9.3 倍。
• NeurIPS 是发水印论文最多的会议，2023–2026 年共 34 篇，占四个会议总量的 34%。
• 交叉方向里涨得最快的是社会层面 · accountability transparency and interpretability：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 18 篇。
• 在「安全与可信」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的验证是 6.0 倍，水印是 9.3 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026Auditing Cross-Lingual Fairness in Language Model Watermarking
• ICML 2026Ideal Attribution and Faithful Watermarks for Language Models
• ICLR 2026An Ensemble Framework for Unbiased Language Model Watermarking
• CVPR 2026Convolutional Neural Networks Driven by Content Similarity
• NeurIPS 2025BitMark: Watermarking Bitwise Autoregressive Image Generative Models
• ICML 2025STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings
• ICLR 2025A Watermark for Order-Agnostic Language Models
• CVPR 2025OmniGuard: Hybrid Manipulation Localization via Augmented Versatile Deep Image Watermarking
• NeurIPS 2024FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent Space
• ICML 2024DE-COP: Detecting Copyrighted Content in Language Models Training Data
• ICLR 2024On the Learnability of Watermarks for Language Models
• CVPR 2024EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protection
• NeurIPS 2023An information-theoretic quantification of the content of communication between brain regions
• ICML 2023Margin-based Neural Network Watermarking
• CVPR 2023CAP-VSTNet: Content Affinity Preserved Versatile Style Transfer
• NeurIPS 2026Face Deepfake-aware Recovery via Semantic-driven Facial Representation-based Watermarking
• ICML 2026Towards Reliable Marking and Verification of AI-Generated Text via Geometry-aware Sentence-level Watermarking
• ICLR 2026Analyzing and Evaluating Unbiased Language Model Watermark
• CVPR 2026Decoupling Defense Strategies for Robust Image Watermarking
• NeurIPS 2025Provable Watermarking for Data Poisoning Attacks

全部水印论文

共 101 篇，第 2 / 3 页

51. NeurIPS 2026Secure Seed-Based Multi-bit Watermarking for Diffusion Models from First Principles
52. NeurIPS 2026Sequential Behavioral Watermarking for LLM Agents
53. NeurIPS 2026TRACE: Structure-Aware Character Encoding for Robust and Generalizable Document Watermarking
54. NeurIPS 2026Watermarking as a Learned Intrinsic Property of Diffusion Models
55. NeurIPS 2026Watermarking Game-Playing Agents in Perfect-Information Extensive-Form Games
56. NeurIPS 2026Watermarking Without Standards Is Not AI Governance
57. CVPR 20253D-GSW: 3D Gaussian Splatting for Robust Watermarking
58. CVPR 2025GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting
59. CVPR 2025OmniGuard: Hybrid Manipulation Localization via Augmented Versatile Deep Image Watermarking
60. CVPR 2025Watermarking One for All: A Robust Watermarking Scheme Against Partial Image Theft
61. ICLR 2025A Watermark for Order-Agnostic Language Models
62. ICLR 2025Hidden in the Noise: Two-Stage Robust Watermarking for Images
63. ICML 2025An End-to-End Model for Logits-Based Large Language Models Watermarking
64. ICML 2025BiMark: Unbiased Multilayer Watermarking for Large Language Models
65. ICML 2025De-mark: Watermark Removal in Large Language Models
66. ICML 2025GaussMark: A Practical Approach for Structural Watermarking of Language Models
67. ICML 2025Lightweight-Mark: Rethinking Deep Learning-Based Watermarking
68. ICML 2025STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings
69. NeurIPS 2025BitMark: Watermarking Bitwise Autoregressive Image Generative Models
70. NeurIPS 2025Mask Image Watermarking
71. NeurIPS 2025On the Coexistence and Ensembling of Watermarks
72. NeurIPS 2025Practical and Effective Code Watermarking for Large Language Models
73. NeurIPS 2025Provable Watermarking for Data Poisoning Attacks
74. NeurIPS 2025RoMa: A Robust Model Watermarking Scheme for Protecting IP in Diffusion Models
75. NeurIPS 2025Shallow Diffuse: Robust and Invisible Watermarking through Low-Dim Subspaces in Diffusion Models
76. NeurIPS 2025Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach
77. NeurIPS 2025Vector Database Watermarking
78. NeurIPS 2025WMCopier: Forging Invisible Watermarks on Arbitrary Images
79. CVPR 2024EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protection
80. CVPR 2024Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models
81. CVPR 2024Generating Content for HDR Deghosting from Frequency View
82. CVPR 2024ProMark: Proactive Diffusion Watermarking for Causal Attribution
83. ICLR 2024On the Learnability of Watermarks for Language Models
84. ICML 2024DE-COP: Detecting Copyrighted Content in Language Models Training Data
85. ICML 2024Defense against Model Extraction Attack by Bayesian Active Watermarking
86. ICML 2024Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews
87. ICML 2024Proactive Detection of Voice Cloning with Localized Watermarking
88. ICML 2024Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models
89. ICML 2024Watermark Stealing in Large Language Models
90. ICML 2024Watermarks in the Sand: Impossibility of Strong Watermarking for Language Models
91. NeurIPS 2024Edit Distance Robust Watermarks via Indexing Pseudorandom Codes
92. NeurIPS 2024FedGMark: Certifiably Robust Watermarking for Federated Graph Learning
93. NeurIPS 2024FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent Space
94. NeurIPS 2024No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices
95. NeurIPS 2024Watermarking Makes Language Models Radioactive
96. CVPR 2023CAP-VSTNet: Content Affinity Preserved Versatile Style Transfer
97. CVPR 2023Wide-Angle Rectification via Content-Aware Conformal Mapping
98. ICML 2023How Bad is Top-$K$ Recommendation under Competing Content Creators?
99. ICML 2023Margin-based Neural Network Watermarking
100. ICML 2023Performative Recommendation: Diversifying Content via Strategic Incentives

常见问题

2023–2026 年四大会议一共有多少篇水印论文？

共 101 篇，按年份分别是 2023 年 6 篇、2024 年 17 篇、2025 年 22 篇、2026 年 56 篇。

NeurIPS 2026 有多少篇水印论文？

NeurIPS 2026 有 18 篇水印论文，上一届是 10 篇。

ICLR 2026 有多少篇水印论文？

ICLR 2026 有 11 篇水印论文，上一届是 2 篇。

ICML 2026 有多少篇水印论文？

ICML 2026 有 16 篇水印论文，上一届是 6 篇。

CVPR 2026 有多少篇水印论文？

CVPR 2026 有 11 篇水印论文，上一届是 4 篇。

哪个会议的水印论文最多？

NeurIPS，2023–2026 年共 34 篇。