Text watermarking algorithms are crucial for protecting the copyright of textual content. Historically, their capabilities and application scenarios were limited. However, recent …
The past 3 years of work in NLP have been characterized by the development and deployment of ever larger language models, especially for English. BERT, its variants, GPT …
Y Wang, Y Pan, M Yan, Z Su… - IEEE Open Journal of the …, 2023 - ieeexplore.ieee.org
With the widespread use of large artificial intelligence (AI) models such as ChatGPT, AI- generated content (AIGC) has garnered increasing attention and is leading a paradigm shift …
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 …
Large language models (LLMs) have shown the ability to produce fluent and cogent content, presenting both productivity opportunities and societal risks. To build trustworthy AI systems …
S Abdelnabi, M Fritz - 2021 IEEE Symposium on Security and …, 2021 - ieeexplore.ieee.org
Recent advances in natural language generation have introduced powerful language models with high-quality output text. However, this raises concerns about the potential …
P Amrit, AK Singh - Computer Communications, 2022 - Elsevier
Recently, machine/deep learning has become a promising solution for some intelligent tasks. It can be actively used for watermarking but less so for conventional tasks such as …
We introduce Ghostbuster, a state-of-the-art system for detecting AI-generated text. Our method works by passing documents through a series of weaker language models, running …