Lost in Overlap: Exploring Logit-based Watermark Collision in LLMs
The proliferation of large language models (LLMs) in generating content raises concerns about text copyright. Watermarking methods, particularly logit-based approaches, embed imperceptible identifiers into text to address these challenges. However, the widespread usage of watermarking across diverse LLMs has led to an inevitable issue known as watermark collision during common tasks, such as paraphrasing or translation. In this paper, we introduce watermark collision as a novel and general philosophy for watermark attacks, aimed at enhancing attack performance on top of any other attacking methods. We also provide a comprehensive demonstration that watermark collision poses a threat to all logit-based watermark algorithms, impacting not only specific attack scenarios but also downstream applications.
Code (0)
등록된 구현이 없습니다.
Tasks
PhilosophyQuestion AnsweringSimilar Papers 제목 키워드 기반
Distortion-free Watermarks are not Truly Distortion-free under Watermark Key Collisions
Language model (LM) watermarking techniques inject a statistical signal into LM-generated content by substituting the random sampling process with pseudo-random sampling, using watermark keys as the random seed. Among th…
Language ModelingLanguage ModellingA Semantic Invariant Robust Watermark for Large Language Models
Watermark algorithms for large language models (LLMs) have achieved extremely high accuracy in detecting text generated by LLMs. Such algorithms typically involve adding extra watermark logits to the LLM's logits at each…
GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trick
Large language models (LLMs) excellently generate human-like text, but also raise concerns about misuse in fake news and academic dishonesty. Decoding-based watermark, particularly the GumbelMax-trick-based watermark(GM …
DiversityLanguage ModelingLanguage ModellingOn the Weaknesses of Backdoor-based Model Watermarking: An Information-theoretic Perspective
Safeguarding the intellectual property of machine learning models has emerged as a pressing concern in AI security. Model watermarking is a powerful technique for protecting ownership of machine learning models, yet its …
PostMark: A Robust Blackbox Watermark for Large Language Models
The most effective techniques to detect LLM-generated text rely on inserting a detectable signature -- or watermark -- during the model's decoding process. Most existing watermarking methods require access to the underly…