paper-with-me

홈 › Papers

TokenMark: A Modality-Agnostic Watermark for Pre-trained Transformers

2024-03-09 · Hengyuan Xu, Liyao Xiang, Borui Yang, Xingjun Ma, Siheng Chen, Baochun Li

Watermarking is a critical tool for model ownership verification. However, existing watermarking techniques are often designed for specific data modalities and downstream tasks, without considering the inherent architectural properties of the model. This lack of generality and robustness underscores the need for a more versatile watermarking approach. In this work, we investigate the properties of Transformer models and propose TokenMark, a modality-agnostic, robust watermarking system for pre-trained models, leveraging the permutation equivariance property. TokenMark embeds the watermark by fine-tuning the pre-trained model on a set of specifically permuted data samples, resulting in a watermarked model that contains two distinct sets of weights -- one for normal functionality and the other for watermark extraction, the latter triggered only by permuted inputs. Extensive experiments on state-of-the-art pre-trained models demonstrate that TokenMark significantly improves the robustness, efficiency, and universality of model watermarking, highlighting its potential as a unified watermarking solution.

📄 PDF Abstract BibTeX arXiv:2403.05842

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Achieving Resolution-Agnostic DNN-based Image Watermarking: A Novel Perspective of Implicit Neural Representation

2024-05-14 · Yuchen Wang, Xingyu Zhu, Guanhui Ye, Shiyao Zhang 외

DNN-based watermarking methods are rapidly developing and delivering impressive performances. Recent advances achieve resolution-agnostic image watermarking by reducing the variant resolution watermarking problem to a fi…

Decoder

Mitigating Watermark Forgery in Generative Models via Randomized Key Selection

2025-07-10 · Toluwani Aremu, Noor Hussein, Munachiso Nwadike, Samuele Poppi 외 arxiv

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 th…

A Watermark for Order-Agnostic Language Models

2024-10-17 · Ruibo Chen, Yihan Wu, Yanshuo Chen, Chenxi Liu 외

Statistical watermarking techniques are well-established for sequentially decoded language models (LMs). However, these techniques cannot be directly applied to order-agnostic LMs, as the tokens in order-agnostic LMs are…

An Empirical Study of Multimodal Model Merging

2023-04-28 · Yi-Lin Sung, Linjie Li, Kevin Lin, Zhe Gan 외

Model merging (e.g., via interpolation or task arithmetic) fuses multiple models trained on different tasks to generate a multi-task solution. The technique has been proven successful in previous studies, where the model…

modelRetrievalTask ArithmeticVisual Question Answering (VQA)

Task-Agnostic Language Model Watermarking via High Entropy Passthrough Layers

2024-12-17 · Vaden Masrani, Mohammad Akbari, David Ming Xuan Yue, Ahmad Rezaei 외

In the era of costly pre-training of large language models, ensuring the intellectual property rights of model owners, and insuring that said models are responsibly deployed, is becoming increasingly important. To this e…

Language ModelingLanguage Modelling