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 1 / 3 页

1. CVPR 2026Convolutional Neural Networks Driven by Content Similarity
2. CVPR 2026Decoupling Defense Strategies for Robust Image Watermarking
3. CVPR 2026Mark4D Temporally-Consistent Watermarking for 4D Gaussian Splatting
4. CVPR 2026MaxMark High-Capacity Diffusion-Native Watermarking via Robust and Invertible Latent Embedding
5. CVPR 2026Meta-FC Meta-Learning with Feature Consistency for Robust and Generalizable Watermarking
6. CVPR 2026PECCVAI Overcoming the Brittleness of AI Image Watermarking Under Visual
7. CVPR 2026RecoverMark Robust Watermarking for Localization and Recovery of Manipulated Faces
8. CVPR 2026Rel-Zero Harnessing Patch-Pair Invariance for Robust Zero-Watermarking Against AI Editing
9. CVPR 2026TIACam Text-Anchored Invariant Feature Learning with Auto-Augmentation for Camera-Robust Zero-Watermarking
10. CVPR 2026Where What Why Toward Explainable 3D-GS Watermarking
11. CVPR 2026You Only Erase Once Erasing Anything without Bringing Unexpected Content
12. ICLR 2026An Ensemble Framework for Unbiased Language Model Watermarking
13. ICLR 2026Analyzing and Evaluating Unbiased Language Model Watermark
14. ICLR 2026Attack-Resistant Watermarking for AIGC Image Forensics via Diffusion-based Semantic Deflection
15. ICLR 2026CompMarkGS: Robust Watermarking for Compressed 3D Gaussian Splatting
16. ICLR 2026MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection
17. ICLR 2026NoisePrints: Distortion-Free Watermarks for Authorship in Private Diffusion Models
18. ICLR 2026PMark: Towards Robust and Distortion-free Semantic-level Watermarking with Channel Constraints
19. ICLR 2026Spherical Watermark: Encryption-Free, Lossless Watermarking for Diffusion Models
20. ICLR 2026THE SELF-RE-WATERMARKING TRAP: FROM EXPLOIT TO RESILIENCE
21. ICLR 2026WaterDrum: Watermark-based Data-centric Unlearning Metric
22. ICLR 2026Watermarking Diffusion Language Models
23. ICML 2026Beyond Heuristic Tuning: Power-Calibrated LLM Watermarking
24. ICML 2026Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarking
25. ICML 2026Catch-22: On the Fundamental Tradeoff Between Detectability and Robustness in LLM Watermarking
26. ICML 2026Collaborative Threshold Watermarking
27. ICML 2026dgMARK: Decoding-Guided Watermarking for Diffusion Language Models
28. ICML 2026Echoes within the Reasoning: Stealthy and Effective Watermarking via Chain of Thought
29. ICML 2026How Good is Post-Hoc Watermarking With Language Model Rephrasing?
30. ICML 2026IACW: Intent-Aware Controllable Watermarking for Scalable Authorial Intent Attribution
31. ICML 2026Ideal Attribution and Faithful Watermarks for Language Models
32. ICML 2026LLM Self-Recognition: Steering and Retrieving Activation Signatures
33. ICML 2026Revisiting Coding-Based Approaches to Overcome the Curse of Dimensionality in Learning-Based Watermarking
34. ICML 2026Rotation-Invariant Spherical Watermarking via Third-Order SO(3) Representation Coupling
35. ICML 2026Selective Disclosure Watermarking for Large Language Models
36. ICML 2026Towards Reliable Marking and Verification of AI-Generated Text via Geometry-aware Sentence-level Watermarking
37. ICML 2026Watermarking Graph Neural Networks via Explanations for Ownership Protection
38. ICML 2026Watermarking LLM Agent Trajectories
39. NeurIPS 2026A Locally Tokenized Generative Model for Robust Time-Series Watermarking
40. NeurIPS 2026Asymmetric Phase Coding Audio Watermarking
41. NeurIPS 2026Auditing Cross-Lingual Fairness in Language Model Watermarking
42. NeurIPS 2026Face Deepfake-aware Recovery via Semantic-driven Facial Representation-based Watermarking
43. NeurIPS 2026Invisible Ink, Visible Lies: How Production Watermarking Causes LLMs to Hallucinate
44. NeurIPS 2026Majority Bit-Aware Watermarking for Large Language Models
45. NeurIPS 2026MarkTune: Improving the Quality-Detectability Trade-off in Model-Embedded LLM Watermarking
46. NeurIPS 2026MC$^2$Mark: Distortion-Free Multi-Bit Watermarking for Long Messages
47. NeurIPS 2026Multi-bit LLM Watermarking with Certified Semantic Distortion
48. NeurIPS 2026PP-Mark: Provable and Publicly Verifiable Watermarking for Generative AI
49. NeurIPS 2026Reading the Finetuning Prior: Verbatim Content Recovery via Contrastive Decoding Diffing
50. NeurIPS 2026Robust and Hard-to-Remove GNN Watermarking via Topological Invariant Perception

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。