English
Related papers

Related papers: Performance-lossless Black-box Model Watermarking

200 papers

Graph Neural Networks (GNNs) have achieved promising performance in various real-world applications. Building a powerful GNN model is not a trivial task, as it requires a large amount of training data, powerful computing resources, and…

Machine Learning · Computer Science 2022-11-15 Jing Xu , Stefanos Koffas , Oguzhan Ersoy , Stjepan Picek

We propose a novel multi-bit box-free watermarking method for the protection of Intellectual Property Rights (IPR) of GANs with improved robustness against white-box attacks like fine-tuning, pruning, quantization, and surrogate model…

Computer Vision and Pattern Recognition · Computer Science 2023-10-27 Jianwei Fei , Zhihua Xia , Benedetta Tondi , Mauro Barni

Potential harms of large language models can be mitigated by watermarking model output, i.e., embedding signals into generated text that are invisible to humans but algorithmically detectable from a short span of tokens. We propose a…

Machine Learning · Computer Science 2024-05-03 John Kirchenbauer , Jonas Geiping , Yuxin Wen , Jonathan Katz , Ian Miers , Tom Goldstein

The rapid growth of transformer-based models increases the concerns about their integrity and ownership insurance. Watermarking addresses this issue by embedding a unique identifier into the model, while preserving its performance. However,…

Cryptography and Security · Computer Science 2024-01-19 Pierre Fernandez , Guillaume Couairon , Teddy Furon , Matthijs Douze

Watermarking technology has gained significant attention due to the increasing importance of intellectual property (IP) rights, particularly with the growing deployment of large language models (LLMs) on billions resource-constrained edge…

Cryptography and Security · Computer Science 2025-07-14 Qingxiao Guo , Xinjie Zhu , Yilong Ma , Hui Jin , Yunhao Wang , Weifeng Zhang , Xiaobing Guo

Natural language generation (NLG) applications have gained great popularity due to the powerful deep learning techniques and large training corpus. The deployed NLG models may be stolen or used without authorization, while watermarking has…

Multimedia · Computer Science 2021-12-13 Tao Xiang , Chunlong Xie , Shangwei Guo , Jiwei Li , Tianwei Zhang

Deep neural networks are vulnerable to malicious fine-tuning attacks such as data poisoning and backdoor attacks. Therefore, in recent research, it is proposed how to detect malicious fine-tuning of neural network models. However, it…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Zhaoxia Yin , Heng Yin , Xinpeng Zhang

With the rise of Machine Learning as a Service (MLaaS) platforms,safeguarding the intellectual property of deep learning models is becoming paramount. Among various protective measures, trigger set watermarking has emerged as a flexible and…

Cryptography and Security · Computer Science 2024-04-23 Hongyu Zhu , Sichu Liang , Wentao Hu , Fangqi Li , Ju Jia , Shilin Wang

As deep learning (DL) models are widely and effectively used in Machine Learning as a Service (MLaaS) platforms, there is a rapidly growing interest in DL watermarking techniques that can be used to confirm the ownership of a particular…

Cryptography and Security · Computer Science 2024-11-22 Mikhail Pautov , Nikita Bogdanov , Stanislav Pyatkin , Oleg Rogov , Ivan Oseledets

With the broad application of deep neural networks, the necessity of protecting them as intellectual properties has become evident. Numerous watermarking schemes have been proposed to identify the owner of a deep neural network and verify…

Cryptography and Security · Computer Science 2021-08-23 Fang-Qi Li , Shi-Lin Wang , Alan Wee-Chung Liew

The rapid development of deep learning has benefited from the release of some high-quality open-sourced datasets ($e.g.$, ImageNet), which allows researchers to easily verify the effectiveness of their algorithms. Almost all existing…

Cryptography and Security · Computer Science 2020-11-20 Yiming Li , Ziqi Zhang , Jiawang Bai , Baoyuan Wu , Yong Jiang , Shu-Tao Xia

Diffusion models have rapidly become a vital part of deep generative architectures, given today's increasing demands. Obtaining large, high-performance diffusion models demands significant resources, highlighting their importance as…

Cryptography and Security · Computer Science 2023-11-30 Sen Peng , Yufei Chen , Cong Wang , Xiaohua Jia

Graph Neural Networks (GNNs) are widely deployed in industry, making their intellectual property valuable. However, protecting GNNs from unauthorized use remains a challenge. Watermarking offers a solution by embedding ownership information…

Cryptography and Security · Computer Science 2026-05-12 Jane Downer , Yingdan Shi , Ziyan Liu , Ren Wang , Binghui Wang

Large language models (LLMs) have achieved remarkable success across a wide range of natural language processing tasks, demonstrating human-level performance in text generation, reasoning, and question answering. However, training such…

Cryptography and Security · Computer Science 2025-11-17 Yanbo Dai , Zongjie Li , Zhenlan Ji , Shuai Wang

The intellectual property of deep generative networks (GNets) can be protected using a cascaded hiding network (HNet) which embeds watermarks (or marks) into GNet outputs, known as box-free watermarking. Although both GNet and HNet are…

Cryptography and Security · Computer Science 2025-07-25 Haonan An , Guang Hua , Hangcheng Cao , Zhengru Fang , Guowen Xu , Susanto Rahardja , Yuguang Fang

Watermarking enables GenAI providers to verify whether content was generated by their models. A watermark is a hidden signal in the content, whose presence can be detected using a secret watermark key. A core security threat are forgery…

Cryptography and Security · Computer Science 2026-05-12 Toluwani Aremu , Noor Hussein , Munachiso Nwadike , Samuele Poppi , Jie Zhang , Karthik Nandakumar , Neil Gong , Nils Lukas

Federated Language Model (FedLM) allows a collaborative learning without sharing raw data, yet it introduces a critical vulnerability, as every untrustworthy client may leak the received functional model instance. Current watermarking…

Cryptography and Security · Computer Science 2026-03-13 Haodong Zhao , Jinming Hu , Yijie Bai , Tian Dong , Wei Du , Zhuosheng Zhang , Yanjiao Chen , Haojin Zhu , Gongshen Liu

Large language models (LLMs) have demonstrated outstanding performance, making them valuable digital assets with significant commercial potential. Unfortunately, the LLM and its API are susceptible to intellectual property theft.…

Cryptography and Security · Computer Science 2024-07-25 Shuai Li , Kejiang Chen , Kunsheng Tang , Jie Zhang , Weiming Zhang , Nenghai Yu , Kai Zeng

As open-source large language models (LLMs) like Llama3 become more capable, it is crucial to develop watermarking techniques to detect their potential misuse. Existing watermarking methods either add watermarks during LLM inference, which…

Computation and Language · Computer Science 2025-03-18 Yijie Xu , Aiwei Liu , Xuming Hu , Lijie Wen , Hui Xiong

Protecting the intellectual property of machine learning models is a hot topic and many watermarking schemes for deep neural networks have been proposed in the literature. Unfortunately, prior work largely neglected the investigation of…

Machine Learning · Computer Science 2024-10-08 Stefano Calzavara , Lorenzo Cazzaro , Donald Gera , Salvatore Orlando