Paper Title:
Topic-based Watermarks for LLM-Generated Text
Published on:
2 April 2024
Primary Category:
Cryptography and Security
Paper Authors:
Alexander Nemecek,
Yuzhou Jiang,
Erman Ayday
Proposes topic-based watermarking technique for large language models
Embeds signatures in AI text based on extracted topic(s)
Overcomes limitations in robustness and practicality of prior schemes
Enables feasible watermark detection algorithms at scale
Allows modeling attacker's benefit vs. loss tradeoff
Topic-based watermarking to identify AI text
This paper proposes a new watermarking technique to identify text generated by large language models versus humans. It embeds detectable signatures based on the text's topics, overcoming limitations in previous watermarking schemes that lacked robustness against attacks or practicality at scale. The proposed technique selects inclusion/exclusion token lists according to extracted topics, enabling feasible detection algorithms. It provides modeling of potential attacks' benefits versus losses.
Uncovering the Hidden Signals: A Popular Science Guide to Language Model Watermarking
Detecting and evaluating watermarks in AI text generation
Protecting AI content with deep watermarks
Probabilistic verification of neural network ownership
Mitigating typographic attacks in multimodal models
Detecting AI-generated text across domains
No comments yet, be the first to start the conversation...
Sign up to comment on this paper