Timezone: »

 
Provable Robust Watermarking for AI-Generated Text
Xuandong Zhao · Prabhanjan Ananth · Lei Li · Yu-Xiang Wang

@
in Challenges in Deployable Generative AI »
Event URL: https://openreview.net/forum?id=Bwz0fy9Hc9 »

As AI-generated text increasingly resembles human-written content, the ability to detect machine-generated text becomes crucial. To address this challenge, we present GPTWatermark, a robust and high-quality solution designed to ascertain whether a piece of text originates from a specific model. Our approach extends existing watermarking strategies and employs a fixed group design to enhance robustness against editing and paraphrasing attacks. We show that our watermarked language model enjoys strong provable guarantees on generation quality, correctness in detection, and security against evasion attacks. Experimental results on various large language models (LLMs) and diverse datasets demonstrate that our method achieves superior detection accuracy and comparable generation quality in perplexity, thus promoting the responsible use of LLMs.

Keywords: secure ai · watermark · text generation

Author Information

Xuandong Zhao (UCSB)
Prabhanjan Ananth (, University of California, Santa Barbara)
Lei Li (University of California Santa Barbara)
Yu-Xiang Wang (UC Santa Barbara / Amazon)

More from the Same Authors