Mixer: DNN Watermarking using Image Mixup - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Mixer: DNN Watermarking using Image Mixup

Résumé

It is crucial to protect the intellectual property rights of DNN models prior to their deployment. The DNN should perform two main tasks: its primary task and watermarking task. This paper proposes a lightweight, reliable, and secure DNN watermarking that attempts to establish strong ties between these two tasks. The samples triggering the watermarking task are generated using image Mixup either from training or testing samples. This means that there is an infinity of triggers not limited to the samples used to embed the watermark in the model at training. The extensive experiments on image classification models for different datasets as well as exposing them to a variety of attacks, show that the proposed watermarking provides protection with an adequate level of security and robustness.
Fichier principal
Vignette du fichier
Mixer_DNN_Watermarking_using_Image_Mixup.pdf (2.07 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04112866 , version 1 (01-06-2023)

Licence

Paternité

Identifiants

Citer

Kassem Kallas, Teddy Furon. Mixer: DNN Watermarking using Image Mixup. ICASSP 2023 - IEEE International Conference on Acoustics, Speech and Signal Processing, Jun 2023, Ialyssos, Greece. pp.1-4, ⟨10.1109/icassp49357.2023.10095332⟩. ⟨hal-04112866⟩
38 Consultations
25 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More