On Evaluating The Performance of Watermarked Machine-Generated Texts Under Adversarial Attacks

• URL: http://arxiv.org/abs/2407.04794v1
• Date: Fri, 5 Jul 2024 18:09:06 GMT
• Title: On Evaluating The Performance of Watermarked Machine-Generated Texts Under Adversarial Attacks
• Authors: Zesen Liu, Tianshuo Cong, Xinlei He, Qi Li,
• Abstract summary: We first comb the mainstream watermarking schemes and removal attacks on machine-generated texts. We evaluate eight watermarks (five pre-text, three post-text) and twelve attacks (two pre-text, ten post-text) across 87 scenarios. Results indicate that KGW and Exponential watermarks offer high text quality and watermark retention but remain vulnerable to most attacks.
• Score: 20.972194348901958
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) excel in various applications, including text generation and complex tasks. However, the misuse of LLMs raises concerns about the authenticity and ethical implications of the content they produce, such as deepfake news, academic fraud, and copyright infringement. Watermarking techniques, which embed identifiable markers in machine-generated text, offer a promising solution to these issues by allowing for content verification and origin tracing. Unfortunately, the robustness of current LLM watermarking schemes under potential watermark removal attacks has not been comprehensively explored. In this paper, to fill this gap, we first systematically comb the mainstream watermarking schemes and removal attacks on machine-generated texts, and then we categorize them into pre-text (before text generation) and post-text (after text generation) classes so that we can conduct diversified analyses. In our experiments, we evaluate eight watermarks (five pre-text, three post-text) and twelve attacks (two pre-text, ten post-text) across 87 scenarios. Evaluation results indicate that (1) KGW and Exponential watermarks offer high text quality and watermark retention but remain vulnerable to most attacks; (2) Post-text attacks are found to be more efficient and practical than pre-text attacks; (3) Pre-text watermarks are generally more imperceptible, as they do not alter text fluency, unlike post-text watermarks; (4) Additionally, combined attack methods can significantly increase effectiveness, highlighting the need for more robust watermarking solutions. Our study underscores the vulnerabilities of current techniques and the necessity for developing more resilient schemes.

Related papers

• Revisiting the Robustness of Watermarking to Paraphrasing Attacks [10.68370011459729]
  Many recent watermarking techniques modify the output probabilities of LMs to embed a signal in the generated output that can later be detected. We show that with access to only a limited number of generations from a black-box watermarked model, we can drastically increase the effectiveness of paraphrasing attacks to evade watermark detection.
  arXiv  Detail & Related papers  (2024-11-08T02:22:30Z)
• Topic-Based Watermarks for LLM-Generated Text [46.71493672772134]
  This paper proposes a novel topic-based watermarking algorithm for large language models (LLMs) By using topic-specific token biases, we embed a topic-sensitive watermarking into the generated text. We demonstrate that our proposed watermarking scheme classifies various watermarked text topics with 99.99% confidence.
  arXiv  Detail & Related papers  (2024-04-02T17:49:40Z)
• Duwak: Dual Watermarks in Large Language Models [49.00264962860555]
  We propose, Duwak, to enhance the efficiency and quality of watermarking by embedding dual secret patterns in both token probability distribution and sampling schemes. We evaluate Duwak extensively on Llama2, against four state-of-the-art watermarking techniques and combinations of them.
  arXiv  Detail & Related papers  (2024-03-12T16:25:38Z)
• 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)
• A Survey of Text Watermarking in the Era of Large Language Models [91.36874607025909]
  Text watermarking algorithms are crucial for protecting the copyright of textual content. Recent advancements in large language models (LLMs) have revolutionized these techniques. This paper conducts a comprehensive survey of the current state of text watermarking technology.
  arXiv  Detail & Related papers  (2023-12-13T06:11:42Z)
• Towards Codable Watermarking for Injecting Multi-bits Information to LLMs [86.86436777626959]
  Large language models (LLMs) generate texts with increasing fluency and realism. Existing watermarking methods are encoding-inefficient and cannot flexibly meet the diverse information encoding needs. We propose Codable Text Watermarking for LLMs (CTWL) that allows text watermarks to carry multi-bit customizable information.
  arXiv  Detail & Related papers  (2023-07-29T14:11:15Z)
• Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy [52.765898203824975]
  We introduce a semantic-aware watermarking algorithm that considers the characteristics of conditional text generation and the input context. Experimental results demonstrate that our proposed method yields substantial improvements across various text generation models.
  arXiv  Detail & Related papers  (2023-07-25T20:24:22Z)
• 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)

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.