SoK: Are Watermarks in LLMs Ready for Deployment?
Kieu Dang, Phung Lai, NhatHai Phan, Yelong Shen, Ruoming Jin, Abdallah Khreishah, My T.Thai

TL;DR
This paper systematically reviews watermarking techniques in large language models, analyzing their effectiveness, limitations, and practical challenges to assess readiness for real-world deployment.
Contribution
It introduces a comprehensive taxonomy, a novel IP classifier, and evaluates existing watermarks' limitations and deployment challenges in LLMs.
Findings
Watermarks can impact LLM utility and downstream tasks.
Current watermarking techniques are not fully ready for deployment.
Practical solutions are needed for effective LLM watermarking.
Abstract
Large Language Models (LLMs) have transformed natural language processing, demonstrating impressive capabilities across diverse tasks. However, deploying these models introduces critical risks related to intellectual property violations and potential misuse, particularly as adversaries can imitate these models to steal services or generate misleading outputs. We specifically focus on model stealing attacks, as they are highly relevant to proprietary LLMs and pose a serious threat to their security, revenue, and ethical deployment. While various watermarking techniques have emerged to mitigate these risks, it remains unclear how far the community and industry have progressed in developing and deploying watermarks in LLMs. To bridge this gap, we aim to develop a comprehensive systematization for watermarks in LLMs by 1) presenting a detailed taxonomy for watermarks in LLMs, 2) proposing…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdversarial Robustness in Machine Learning · Advanced Malware Detection Techniques · Physical Unclonable Functions (PUFs) and Hardware Security
MethodsSoftmax · Attention Is All You Need · Focus
