paper-with-me

Papers

Functional Invariants to Watermark Large Transformers

2023-10-17 · Pierre Fernandez, Guillaume Couairon, Teddy Furon, Matthijs Douze

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, most existing approaches require to optimize the weights to imprint the watermark signal, which is not suitable at scale due to the computational cost. This paper explores watermarks with virtually no computational cost, applicable to a non-blind white-box setting (assuming access to both the original and watermarked networks). They generate functionally equivalent copies by leveraging the models' invariance, via operations like dimension permutations or scaling/unscaling. This enables to watermark models without any change in their outputs and remains stealthy. Experiments demonstrate the effectiveness of the approach and its robustness against various model transformations (fine-tuning, quantization, pruning), making it a practical solution to protect the integrity of large models.

📄 PDF Abstract BibTeX arXiv:2310.11446

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Similar Papers 제목 키워드 기반

Invariant-based Robust Weights Watermark for Large Language Models

2025-07-11 · Qingxiao Guo, Xinjie Zhu, Yilong Ma, Hui Jin 외 arxiv

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 resourc…

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

2024-03-09 · Hengyuan Xu, Liyao Xiang, Borui Yang, Xingjun Ma 외

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 architect…

Functional Subspace Watermarking for Large Language Models

2026-03-19 · Zikang Ding, Junhao Li, Suling Wu, Junchi Yao 외 arxiv

Model watermarking utilizes internal representations to protect the ownership of large language models (LLMs). However, these features inevitably undergo complex distortions during realistic model modifications such as f…

Knowledge Distillation

Robust and Secure Code Watermarking for Large Language Models via ML/Crypto Codesign

2025-02-04 · Ruisi Zhang, Neusha Javidnia, Nojan Sheybani, Farinaz Koushanfar

This paper introduces RoSeMary, the first-of-its-kind ML/Crypto codesign watermarking framework that regulates LLM-generated code to avoid intellectual property rights violations and inappropriate misuse in software deve…

Robust GNN Watermarking via Implicit Perception of Topological Invariants

2025-10-29 · Jipeng Li, Yannning Shen arxiv

Graph Neural Networks (GNNs) are valuable intellectual property, yet many watermarks rely on backdoor triggers that break under common model edits and create ownership ambiguity. We present InvGNN-WM, which ties ownershi…

Knowledge DistillationGraph Classification