Related papers: Watermarking Needs Input Repetition Masking

Watermarking Needs Input Repetition Masking

URL: http://arxiv.org/abs/2504.12229v1
Date: Wed, 16 Apr 2025 16:25:26 GMT
Title: Watermarking Needs Input Repetition Masking
Authors: David Khachaturov, Robert Mullins, Ilia Shumailov, Sumanth Dathathri,
Abstract summary: We show that both humans and Large Language Models (LLMs) end up mimicking, including the watermarking signal even in seemingly improbable settings.<n>This challenges current academic assumptions and suggests that for long-term watermarking to be reliable, the likelihood of false positives needs to be significantly lower.
Score: 13.309409725789433
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Recent advancements in Large Language Models (LLMs) raised concerns over potential misuse, such as for spreading misinformation. In response two counter measures emerged: machine learning-based detectors that predict if text is synthetic, and LLM watermarking, which subtly marks generated text for identification and attribution. Meanwhile, humans are known to adjust language to their conversational partners both syntactically and lexically. By implication, it is possible that humans or unwatermarked LLMs could unintentionally mimic properties of LLM generated text, making counter measures unreliable. In this work we investigate the extent to which such conversational adaptation happens. We call the concept $\textit{mimicry}$ and demonstrate that both humans and LLMs end up mimicking, including the watermarking signal even in seemingly improbable settings. This challenges current academic assumptions and suggests that for long-term watermarking to be reliable, the likelihood of false positives needs to be significantly lower, while longer word sequences should be used for seeding watermarking mechanisms.

Related papers

Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data? [62.72729485995075]
We investigate the effectiveness of watermarking as a deterrent against the generation of copyrighted texts. We find that watermarking adversely affects the success rate of Membership Inference Attacks (MIAs) We propose an adaptive technique to improve the success rate of a recent MIA under watermarking.
arXiv Detail & Related papers (2024-07-24T16:53:09Z)
Less is More: Sparse Watermarking in LLMs with Enhanced Text Quality [27.592486717044455]
We present a novel type of watermark, Sparse Watermark, which aims to mitigate this trade-off by applying watermarks to a small subset of generated tokens distributed across the text. Our experimental results demonstrate that the proposed watermarking scheme achieves high detectability while generating text that outperforms previous watermarking methods in quality across various tasks.
arXiv Detail & Related papers (2024-07-17T18:52:12Z)
Large Language Model Watermark Stealing With Mixed Integer Programming [51.336009662771396]
Large Language Model (LLM) watermark shows promise in addressing copyright, monitoring AI-generated text, and preventing its misuse. Recent research indicates that watermarking methods using numerous keys are susceptible to removal attacks. We propose a novel green list stealing attack against the state-of-the-art LLM watermark scheme.
arXiv Detail & Related papers (2024-05-30T04:11:17Z)
WatME: Towards Lossless Watermarking Through Lexical Redundancy [58.61972059246715]
This study assesses the impact of watermarking on different capabilities of large language models (LLMs) from a cognitive science lens. We introduce Watermarking with Mutual Exclusion (WatME) to seamlessly integrate watermarks.
arXiv Detail & Related papers (2023-11-16T11:58:31Z)
Downstream Trade-offs of a Family of Text Watermarks [25.408313192999504]
We evaluate the performance of LLMs watermarked using three different strategies over a diverse suite of tasks. We find that watermarks can cause significant drops in LLMs' effective utility across all tasks. Our findings highlight the trade-offs that users should be cognizant of when using watermarked models.
arXiv Detail & Related papers (2023-11-16T11:44:58Z)
A Robust Semantics-based Watermark for Large Language Model against Paraphrasing [50.84892876636013]
Large language models (LLMs) have show great ability in various natural language tasks. There are concerns that LLMs are possible to be used improperly or even illegally. We propose a semantics-based watermark framework SemaMark.
arXiv Detail & Related papers (2023-11-15T06:19:02Z)
Towards Codable Watermarking for Injecting Multi-bits Information to LLMs [86.86436777626959]
Large language models (LLMs) generate texts with increasing fluency and realism. Existing watermarking methods are encoding-inefficient and cannot flexibly meet the diverse information encoding needs. We propose Codable Text Watermarking for LLMs (CTWL) that allows text watermarks to carry multi-bit customizable information.
arXiv Detail & Related papers (2023-07-29T14:11:15Z)
On the Reliability of Watermarks for Large Language Models [95.87476978352659]
We study the robustness of watermarked text after it is re-written by humans, paraphrased by a non-watermarked LLM, or mixed into a longer hand-written document. We find that watermarks remain detectable even after human and machine paraphrasing. We also consider a range of new detection schemes that are sensitive to short spans of watermarked text embedded inside a large document.
arXiv Detail & Related papers (2023-06-07T17:58:48Z)
Can AI-Generated Text be Reliably Detected? [50.95804851595018]
Large Language Models (LLMs) perform impressively well in various applications.<n>The potential for misuse of these models in activities such as plagiarism, generating fake news, and spamming has raised concern about their responsible use.<n>We stress-test the robustness of these AI text detectors in the presence of an attacker.
arXiv Detail & Related papers (2023-03-17T17:53:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.