A survey of text watermarking in the era of large language models

A Liu, L Pan, Y Lu, J Li, X Hu, X Zhang, L Wen… - ACM Computing …, 2024 - dl.acm.org
Text watermarking algorithms are crucial for protecting the copyright of textual content.
Historically, their capabilities and application scenarios were limited. However, recent …

Preventing and detecting misinformation generated by large language models

A Liu, Q Sheng, X Hu - Proceedings of the 47th International ACM SIGIR …, 2024 - dl.acm.org
As large language models (LLMs) become increasingly capable and widely deployed, the
risk of them generating misinformation poses a critical challenge. Misinformation from LLMs …

Markllm: An open-source toolkit for llm watermarking

L Pan, A Liu, Z He, Z Gao, X Zhao, Y Lu, B Zhou… - arXiv preprint arXiv …, 2024 - arxiv.org
LLM watermarking, which embeds imperceptible yet algorithmically detectable signals in
model outputs to identify LLM-generated text, has become crucial in mitigating the potential …

Revisiting the Robustness of Watermarking to Paraphrasing Attacks

S Rastogi, D Pruthi - arXiv preprint arXiv:2411.05277, 2024 - arxiv.org
Amidst rising concerns about the internet being proliferated with content generated from
language models (LMs), watermarking is seen as a principled way to certify whether text …

Can Watermarked LLMs be Identified by Users via Crafted Prompts?

A Liu, S Guan, Y Liu, L Pan, Y Zhang, L Fang… - arXiv preprint arXiv …, 2024 - arxiv.org
Text watermarking for Large Language Models (LLMs) has made significant progress in
detecting LLM outputs and preventing misuse. Current watermarking techniques offer high …

Context-aware Watermark with Semantic Balanced Green-red Lists for Large Language Models

Y Guo, Z Tian, Y Song, T Liu, L Ding… - Proceedings of the 2024 …, 2024 - aclanthology.org
Watermarking enables people to determine whether the text is generated by a specific
model. It injects a unique signature based on the “green-red” list that can be tracked during …

Downstream Trade-offs of a Family of Text Watermarks

A Ajith, S Singh, D Pruthi - Findings of the Association for …, 2024 - aclanthology.org
Watermarking involves implanting an imperceptible signal into generated text that can later
be detected via statistical tests. A prominent family of watermarking strategies for LLMs …

A Certified Robust Watermark For Large Language Models

X Feng, J Liu, K Ren, C Chen - arXiv preprint arXiv:2409.19708, 2024 - arxiv.org
The effectiveness of watermark algorithms in AI-generated text identification has garnered
significant attention. Concurrently, an increasing number of watermark algorithms have been …