Fetching the paper…

Reading the bibliography…

2024

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

Xu, Hengyuan, Xiang, Liyao, Yang, Borui et al.

Original
PDF
Post on X

Understand

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: A Modality-Agnostic Watermark for Pre-trained Transformers · Around

Built on

T. W. Chaundy, P. R. Barrett and C. Batey, The Printing of Mathematics
1954
Earlier work this paper cites.
H. Sira-Ramirez, “On the sliding mode control of nonlinear systems,” Syst. Control Lett
1992
Earlier work this paper cites.
R. Ortega, A. Astolfi, G. Bastin, and H. Rodriguez, “Stabilization of food-chain systems using a port-controlled Hamiltonian description,” in Proc. Amer. Control Conf
2000
Earlier work this paper cites.

Similar

F. Mittelbach and M. Goossens, The L a
2004
Cited alongside, same era.
A. Levant, “Exact differentiation of signals with unbounded higher derivatives,” in Proc. 45th IEEE Conf. Decis. Control
2006
Cited alongside, same era.
Mathematics Into Type
Cited in the paper.
M. Letourneau and J. W. Sharp, AMS-StyleGuide-online.pdf,
Cited in the paper.

Then

G. Grätzer, More Math Into LaTeX
2007
Later among the works it cites.
M. Fliess, C. Join, and H. Sira-Ramirez, “Non-linear estimation is easy,” Int. J. Model., Ident. Control
2008
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…