Watermarking papers, 2023–2026

Key findings

• Watermarking went from 6 papers in 2023 to 56 in 2026, roughly 9.3x in three years.
• NeurIPS publishes the most Watermarking work: 34 papers from 2023 to 2026, 34% of the four-venue total.
• The fastest-growing overlap is with Social aspects · accountability transparency and interpretability: papers tagged with both rose from 0 in 2023 to 18 in 2026.
• Among the 5 topics under Security and Trust, it ranks #3 by 2026 paper count; the fastest grower in the group, Verification, is up 6.0x versus 9.3x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Watermarking papers

32 papers, page 1 of 1

1. ICML 2026Beyond Heuristic Tuning: Power-Calibrated LLM Watermarking
2. ICML 2026Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarking
3. ICML 2026Catch-22: On the Fundamental Tradeoff Between Detectability and Robustness in LLM Watermarking
4. ICML 2026Collaborative Threshold Watermarking
5. ICML 2026dgMARK: Decoding-Guided Watermarking for Diffusion Language Models
6. ICML 2026Echoes within the Reasoning: Stealthy and Effective Watermarking via Chain of Thought
7. ICML 2026How Good is Post-Hoc Watermarking With Language Model Rephrasing?
8. ICML 2026IACW: Intent-Aware Controllable Watermarking for Scalable Authorial Intent Attribution
9. ICML 2026Ideal Attribution and Faithful Watermarks for Language Models
10. ICML 2026LLM Self-Recognition: Steering and Retrieving Activation Signatures
11. ICML 2026Revisiting Coding-Based Approaches to Overcome the Curse of Dimensionality in Learning-Based Watermarking
12. ICML 2026Rotation-Invariant Spherical Watermarking via Third-Order SO(3) Representation Coupling
13. ICML 2026Selective Disclosure Watermarking for Large Language Models
14. ICML 2026Towards Reliable Marking and Verification of AI-Generated Text via Geometry-aware Sentence-level Watermarking
15. ICML 2026Watermarking Graph Neural Networks via Explanations for Ownership Protection
16. ICML 2026Watermarking LLM Agent Trajectories
17. ICML 2025An End-to-End Model for Logits-Based Large Language Models Watermarking
18. ICML 2025BiMark: Unbiased Multilayer Watermarking for Large Language Models
19. ICML 2025De-mark: Watermark Removal in Large Language Models
20. ICML 2025GaussMark: A Practical Approach for Structural Watermarking of Language Models
21. ICML 2025Lightweight-Mark: Rethinking Deep Learning-Based Watermarking
22. ICML 2025STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings
23. ICML 2024DE-COP: Detecting Copyrighted Content in Language Models Training Data
24. ICML 2024Defense against Model Extraction Attack by Bayesian Active Watermarking
25. ICML 2024Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews
26. ICML 2024Proactive Detection of Voice Cloning with Localized Watermarking
27. ICML 2024Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models
28. ICML 2024Watermark Stealing in Large Language Models
29. ICML 2024Watermarks in the Sand: Impossibility of Strong Watermarking for Language Models
30. ICML 2023How Bad is Top-$K$ Recommendation under Competing Content Creators?
31. ICML 2023Margin-based Neural Network Watermarking
32. ICML 2023Performative Recommendation: Diversifying Content via Strategic Incentives

FAQ

How many Watermarking papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

101 in total: 6 in 2023, 17 in 2024, 22 in 2025, 56 in 2026.

How many Watermarking papers are at NeurIPS 2026?

NeurIPS 2026 has 18 Watermarking papers, versus 10 the year before.

How many Watermarking papers are at ICLR 2026?

ICLR 2026 has 11 Watermarking papers, versus 2 the year before.

How many Watermarking papers are at ICML 2026?

ICML 2026 has 16 Watermarking papers, versus 6 the year before.

How many Watermarking papers are at CVPR 2026?

CVPR 2026 has 11 Watermarking papers, versus 4 the year before.

Which conference publishes the most Watermarking papers?

NeurIPS, with 34 papers from 2023 to 2026.