English
Related papers

Related papers: Watermarking Degrades Alignment in Language Models…

200 papers

In recent years, there has been significant advancement in the field of model watermarking techniques. However, the protection of image-processing neural networks remains a challenge, with only a limited number of methods being developed.…

Cryptography and Security · Computer Science 2023-02-20 Huajie Chen , Tianqing Zhu , Chi Liu , Shui Yu , Wanlei Zhou

Large language models (LLMs) are now rapidly advancing and surpassing human abilities on many natural language tasks. However, aligning these super-human LLMs with human knowledge remains challenging because the supervision signals from…

Computation and Language · Computer Science 2024-06-28 Yue Guo , Yi Yang

The advent of high-quality video generation models has amplified the need for robust watermarking schemes that can be used to reliably detect and track the provenance of generated videos. Existing video watermarking methods based on both…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Samar Fares , Nurbek Tastan , Karthik Nandakumar

Watermarking aims to embed hidden signals in generated text that can be reliably detected when given access to a secret key. Open-weight language models pose acute challenges for such watermarking schemes because the inference-time…

Machine Learning · Computer Science 2025-12-04 Yizhou Zhao , Zhiwei Steven Wu , Adam Block

The widespread use of Large Language Models (LLMs) in text generation has raised increasing concerns about intellectual property disputes. Watermarking techniques, which embed meta information into AI-generated content (AIGC), have the…

Cryptography and Security · Computer Science 2026-04-15 Shangkun Che , Silin Du , Ge Gao

The rise of Large Language Models (LLMs) has heightened concerns about the misuse of AI-generated text, making watermarking a promising solution. Mainstream watermarking schemes for LLMs fall into two categories: logits-based and…

Computation and Language · Computer Science 2025-05-19 Yidan Wang , Yubing Ren , Yanan Cao , Binxing Fang

With the rapid development of cloud-based services, large language models have become increasingly accessible through various web platforms. However, this accessibility has also led to growing risks of model abuse. LLM watermarking has…

Cryptography and Security · Computer Science 2026-04-28 Hao Li , Yubing Ren , Yanan Cao , Yingjie Li , Fang Fang , Shi Wang , Li Guo

Text watermarks in large language models (LLMs) are an increasingly important tool for detecting synthetic text and distinguishing human-written content from LLM-generated text. While most existing studies focus on determining whether…

Machine Learning · Statistics 2025-06-30 Xiang Li , Garrett Wen , Weiqing He , Jiayuan Wu , Qi Long , Weijie J. Su

The Large Language Model (LLM) watermark is a newly emerging technique that shows promise in addressing concerns surrounding LLM copyright, monitoring AI-generated text, and preventing its misuse. The LLM watermark scheme commonly includes…

Cryptography and Security · Computer Science 2024-05-31 Zhaoxi Zhang , Xiaomei Zhang , Yanjun Zhang , Leo Yu Zhang , Chao Chen , Shengshan Hu , Asif Gill , Shirui Pan

Large language models fine-tuned via a two-stage pipeline (domain adaptation followed by instruction alignment) can exhibit non-trivial interference after adapter merging, including the re-emergence of explicit reasoning traces under strict…

Computation and Language · Computer Science 2026-02-12 Junyi Zou

Recent advancements in watermarking techniques have enabled the embedding of secret messages into AI-generated text (AIGT), serving as an important mechanism for AIGT detection. Existing methods typically interfere with the generation…

Cryptography and Security · Computer Science 2025-06-10 Peiru Yang , Xintian Li , Wanchun Ni , Jinhua Yin , Huili Wang , Guoshun Nan , Shangguang Wang , Yongfeng Huang , Tao Qi

Language model benchmarks are pervasive and computationally-efficient proxies for real-world performance. However, many recent works find that benchmarks often fail to predict real utility. Towards bridging this gap, we introduce benchmark…

Artificial Intelligence · Computer Science 2026-05-28 Marco Gutierrez , Xinyi Leng , Hannah Cyberey , Jonathan Richard Schwarz , Ahmed Alaa , Thomas Hartvigsen

Methods for watermarking large language models have been proposed that distinguish AI-generated text from human-generated text by slightly altering the model output distribution, but they also distort the quality of the text, exposing the…

Computation and Language · Computer Science 2024-02-27 Massieh Kordi Boroujeny , Ya Jiang , Kai Zeng , Brian Mark

Recent work has shown that a model's input word embeddings can serve as effective control variables for steering its behavior toward outputs that satisfy desired properties. However, this has only been demonstrated for pretrained…

Computation and Language · Computer Science 2026-04-30 Baturay Saglam , Dionysis Kalogerias

The rapid proliferation of generative audio synthesis and editing technologies has raised serious concerns about copyright infringement, data provenance, and the spread of misinformation via deepfake audio. Watermarking offers a proactive…

Sound · Computer Science 2026-05-25 Yixin Liu , Lie Lu , Jihui Jin , Lichao Sun , Andrea Fanelli

Generation-time text watermarking embeds statistical signals into text for traceability of AI-generated content. We explore *post-hoc watermarking* where an LLM rewrites existing text while applying generation-time watermarking, to protect…

Watermarking has become one of promising techniques to not only aid in identifying AI-generated images but also serve as a deterrent against the unethical use of these models. However, the robustness of watermarking techniques has not been…

Cryptography and Security · Computer Science 2024-11-05 Xiaodong Wu , Xiangman Li , Jianbing Ni

Well-performed deep neural networks (DNNs) generally require massive labelled data and computational resources for training. Various watermarking techniques are proposed to protect such intellectual properties (IPs), wherein the DNN…

Computer Vision and Pattern Recognition · Computer Science 2023-04-04 Xiangyu Wen , Yu Li , Wei Jiang , Qiang Xu

The increasing deployment of intelligent agents in digital ecosystems, such as social media platforms, has raised significant concerns about traceability and accountability, particularly in cybersecurity and digital content protection.…

Artificial Intelligence · Computer Science 2025-08-08 Kaibo Huang , Zipei Zhang , Zhongliang Yang , Linna Zhou

Data watermarking in language models injects traceable signals, such as specific token sequences or stylistic patterns, into copyrighted text, allowing copyright holders to track and verify training data ownership. Previous data…

Cryptography and Security · Computer Science 2025-07-29 Xinyue Cui , Johnny Tian-Zheng Wei , Swabha Swayamdipta , Robin Jia