TokenMark: A Modality-Agnostic Watermark for Pre-trained Transformers
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.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Achieving Resolution-Agnostic DNN-based Image Watermarking: A Novel Perspective of Implicit Neural Representation
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…
DecoderMitigating Watermark Forgery in Generative Models via Randomized Key Selection
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
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
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
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