PURA: Provably Unbiased and Robust Multi-Bit Watermarking for AI-Generated Text Attribution

arXiv:2608.22218 · cs.CR · Submitted 2026-08-23 · Read on arXiv

cs.CR

Submitted: 2026-08-23

Updated: 2026-08-25

Comments: Accepted to ACM CCS 2026

Code: https://github.com/anshigaoa/PURA

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Verifier — 35× in this paper · explained in 2 episodes
• Accuracy — 23× in this paper · explained in 1 episode
• Robustness — 22× in this paper · explained in 5 episodes
• Verification — 19× in this paper · explained in 2 episodes
• Aggregation — 9× in this paper · explained in 1 episode
• Provenance — 6× in this paper · explained in 4 episodes
• International Conference on Machine Learning — 5× in this paper
• Ablation — 4× in this paper · explained in 1 episode
• Accountability — 4× in this paper · explained in 2 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Redundancy — 3× in this paper · explained in 2 episodes
• AUC — 2× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Decode — 2× in this paper · explained in 2 episodes
• IEEE Symposium on Security and Privacy — 2× in this paper
• Network and Distributed System Security Symposium — 2× in this paper
• AI Alignment — 1× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• EMMA — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Optimal Transport — 1× in this paper · explained in 5 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Semantic Drift — 1× in this paper · explained in 3 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Transfer Learning — 1× in this paper · explained in 10 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• MC$^2$Mark: Distortion-Free Multi-Bit Watermarking for Long Messages
• ArcMark: Distortion-Free Multi-Byte LLM Watermark via Optimal Transport
• The Llama 3 Herd of Models
• Pointer Sentinel Mixture Models
• GPT-4 Technical Report
• Gemma 2: Improving Open Language Models at a Practical Size
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
• Qwen2 Technical Report

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs