Text watermarking algorithms are crucial for protecting the copyright of textual content.
Historically, their capabilities and application scenarios were limited. However, recent …

Potential harms of large language models can be mitigated by watermarking model output,
ie, embedding signals into generated text that are invisible to humans but algorithmically …

The unregulated use of LLMs can potentially lead to malicious consequences such as
plagiarism, generating fake news, spamming, etc. Therefore, reliable detection of AI …

ACM: Digital Library: Communications of the ACM ACM Digital Library Communications of the
ACM Volume 67, Number 4 (2024), Pages 50-59 The Science of Detecting LLM-Generated Text …

Recent advances in the capabilities of large language models such as GPT-4 have spurred
increasing concern about our ability to detect AI-generated text. Prior works have suggested …

During the recent years, the issue of preserving the integrity of digital text has become a
focus of interest in the transmission of online content on the Internet. Watermarking has a …

Every major technical invention resurfaces the dual-use dilemma—the new technology has
the potential to be used for good as well as for harm. Generative AI (GenAI) techniques, such …

We propose a methodology for planting watermarks in text from an autoregressive language
model that are robust to perturbations without changing the distribution over text up to a …

The recent advancements in large language models (LLMs) have sparked a growing
apprehension regarding the potential misuse. One approach to mitigating this risk is to …

As AI-generated text increasingly resembles human-written content, the ability to detect
machine-generated text becomes crucial. To address this challenge, we present …