Dataset Watermarking with Provable Black-Box Detection

arXiv:2605.06865 · cs.LG · Submitted 2026-05-07 · Read on arXiv

cs.LG

Submitted: 2026-05-07

Updated: 2026-09-28

Terminology

• Benchmark — 3× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes

Sources

• Extracting Training Data from Large Language Models
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation
• The Llama 3 Herd of Models
• Measuring Massive Multitask Language Understanding
• LoRA: Low-Rank Adaptation of Large Language Models
• Investigating Data Contamination for Pre-training Language Models
• Waterfall: Framework for Robust and Scalable Text Watermarking and Provenance for LLMs
• LLM Dataset Inference: Did you train on my dataset?
• Do SSL Models Have D'ej\`a Vu? A Case of Unintended Memorization in Self-supervised Learning
• Watermarking Makes Language Models Radioactive
• Detecting Benchmark Contamination Through Watermarking
• Detecting Pretraining Data from Large Language Models
• Evaluation data contamination in LLMs: how do we measure it and (when) does it matter?
• Gemma 2: Improving Open Language Models at a Practical Size
• SLIM: Stealthy Low-Coverage Black-Box Watermarking via Latent-Space Confusion Zones
• Understanding Rare Spurious Correlations in Neural Networks
• Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting
• Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models
• A Careful Examination of Large Language Model Performance on Grade School Arithmetic

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks