RoSe: A RObust and SEcure Black-Box DNN Watermarking - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year :

RoSe: A RObust and SEcure Black-Box DNN Watermarking

Abstract

Protecting the Intellectual Property rights of DNN models is of primary importance prior to their deployment. So far, the proposed methods either necessitate changes to internal model parameters or the machine learning pipeline, or they fail to meet both the security and robustness requirements. This paper proposes a lightweight, robust, and secure black-box DNN watermarking protocol that takes advantage of cryptographic one-way functions as well as the injection of in-task key imagelabel pairs during the training process. These pairs are later used to prove DNN model ownership during testing. The main feature is that the value of the proof and its security are measurable. The extensive experiments watermarking image classification models for various datasets as well as exposing them to a variety of attacks, show that it provides protection while maintaining an adequate level of security and robustness.
Fichier principal
Vignette du fichier
WIFS_2022-2.pdf (2.4 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03806393 , version 1 (07-10-2022)

Identifiers

  • HAL Id : hal-03806393 , version 1

Cite

Kassem Kallas, Teddy Furon. RoSe: A RObust and SEcure Black-Box DNN Watermarking. WIFS 2022 - IEEE 14th International Workshop on Information Forensics and Security, Dec 2022, Shanghai, China. pp.1-5. ⟨hal-03806393⟩
68 View
67 Download

Share

Gmail Facebook Twitter LinkedIn More