Watermark Smoothing Attacks against Language Models
- URL: http://arxiv.org/abs/2407.14206v1
- Date: Fri, 19 Jul 2024 11:04:54 GMT
- Title: Watermark Smoothing Attacks against Language Models
- Authors: Hongyan Chang, Hamed Hassani, Reza Shokri,
- Abstract summary: We introduce smoothing attacks and show that existing watermarking methods are not robust against minor modifications of text.
Our attack reveals a fundamental limitation of a wide range of watermarking techniques.
- Score: 40.02225709485305
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Watermarking is a technique used to embed a hidden signal in the probability distribution of text generated by large language models (LLMs), enabling attribution of the text to the originating model. We introduce smoothing attacks and show that existing watermarking methods are not robust against minor modifications of text. An adversary can use weaker language models to smooth out the distribution perturbations caused by watermarks without significantly compromising the quality of the generated text. The modified text resulting from the smoothing attack remains close to the distribution of text that the original model (without watermark) would have produced. Our attack reveals a fundamental limitation of a wide range of watermarking techniques.
Related papers
- Watermarking Language Models with Error Correcting Codes [41.21656847672627]
We propose a watermarking framework that encodes statistical signals through an error correcting code.
Our method, termed robust binary code (RBC) watermark, introduces no distortion compared to the original probability distribution.
Our empirical findings suggest our watermark is fast, powerful, and robust, comparing favorably to the state-of-the-art.
arXiv Detail & Related papers (2024-06-12T05:13:09Z) - Multi-Bit Distortion-Free Watermarking for Large Language Models [4.7381853007029475]
We extend an existing zero-bit distortion-free watermarking method by embedding multiple bits of meta-information as part of the watermark.
We also develop a computationally efficient decoder that extracts the embedded information from the watermark with low bit error rate.
arXiv Detail & Related papers (2024-02-26T14:01:34Z) - Adaptive Text Watermark for Large Language Models [8.100123266517299]
It is challenging to generate high-quality watermarked text while maintaining strong security, robustness, and the ability to detect watermarks without prior knowledge of the prompt or model.
This paper proposes an adaptive watermarking strategy to address this problem.
arXiv Detail & Related papers (2024-01-25T03:57:12Z) - On the Learnability of Watermarks for Language Models [80.97358663708592]
We ask whether language models can directly learn to generate watermarked text.
We propose watermark distillation, which trains a student model to behave like a teacher model.
We find that models can learn to generate watermarked text with high detectability.
arXiv Detail & Related papers (2023-12-07T17:41:44Z) - Improving the Generation Quality of Watermarked Large Language Models
via Word Importance Scoring [81.62249424226084]
Token-level watermarking inserts watermarks in the generated texts by altering the token probability distributions.
This watermarking algorithm alters the logits during generation, which can lead to a downgraded text quality.
We propose to improve the quality of texts generated by a watermarked language model by Watermarking with Importance Scoring (WIS)
arXiv Detail & Related papers (2023-11-16T08:36:00Z) - T2IW: Joint Text to Image & Watermark Generation [74.20148555503127]
We introduce a novel task for the joint generation of text to image and watermark (T2IW)
This T2IW scheme ensures minimal damage to image quality when generating a compound image by forcing the semantic feature and the watermark signal to be compatible in pixels.
We demonstrate remarkable achievements in image quality, watermark invisibility, and watermark robustness, supported by our proposed set of evaluation metrics.
arXiv Detail & Related papers (2023-09-07T16:12:06Z) - On the Reliability of Watermarks for Large Language Models [95.87476978352659]
We study the robustness of watermarked text after it is re-written by humans, paraphrased by a non-watermarked LLM, or mixed into a longer hand-written document.
We find that watermarks remain detectable even after human and machine paraphrasing.
We also consider a range of new detection schemes that are sensitive to short spans of watermarked text embedded inside a large document.
arXiv Detail & Related papers (2023-06-07T17:58:48Z) - A Watermark for Large Language Models [84.95327142027183]
We propose a watermarking framework for proprietary language models.
The watermark can be embedded with negligible impact on text quality.
It can be detected using an efficient open-source algorithm without access to the language model API or parameters.
arXiv Detail & Related papers (2023-01-24T18:52:59Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.