On the Difficulty of Constructing a Robust and Publicly-Detectable Watermark
This work investigates the theoretical boundaries of creating publicly-detectable schemes to enable the provenance of watermarked imagery. Metadata-based approaches like C2PA provide unforgeability and public-detectability. ML techniques offer robust retrieval and watermarking. However, no existing scheme combines robustness, unforgeability, and public-detectability. In this work, we formally define such a scheme and establish its existence. Although theoretically possible, we find that at present, it is intractable to build certain components of our scheme without a leap in deep learning capabilities. We analyze these limitations and propose research directions that need to be addressed before we can practically realize robust and publicly-verifiable provenance.
Code (0)
등록된 구현이 없습니다.
Tasks
RetrievalSimilar Papers 제목 키워드 기반
Publicly-Detectable Watermarking for Language Models
We present a publicly-detectable watermarking scheme for LMs: the detection algorithm contains no secret information, and it is executable by anyone. We embed a publicly-verifiable cryptographic signature into LM output …
Undetectable Watermarks for Language Models
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 methods of embedding watermarks in mode…
An Undetectable Watermark for Generative Image Models
We present the first undetectable watermarking scheme for generative image models. Undetectability ensures that no efficient adversary can distinguish between watermarked and un-watermarked images, even after making many…
Watermarking Language Models for Many Adaptive Users
We study watermarking schemes for language models with provable guarantees. As we show, prior works offer no robustness guarantees against adaptive prompting: when a user queries a language model more than once, as even …
Language ModellingLearning to Watermark LLM-generated Text via Reinforcement Learning
We study how to watermark LLM outputs, i.e. embedding algorithmically detectable signals into LLM-generated text to track misuse. Unlike the current mainstream methods that work with a fixed LLM, we expand the watermark …
reinforcement-learningReinforcement Learning