TATTOOED: A Robust Deep Neural Network Watermarking Scheme based on Spread-Spectrum Channel Coding

02/12/2022
by   Giulio Pagnotta, et al.
0

The proliferation of deep learning applications in several areas has led to the rapid adoption of such solutions from an ever-growing number of institutions and companies. These entities' deep neural network (DNN) models are often trained on proprietary data. They require powerful computational resources, with the resulting DNN models being incorporated in the company's work pipeline or provided as a service. Being trained on proprietary information, these models provide a competitive edge for the owner company. At the same time, these models can be attractive to competitors (or malicious entities), which can employ state-of-the-art security attacks to obtain and use these models for their benefit. As these attacks are hard to prevent, it becomes imperative to have mechanisms that enable an affected entity to verify the ownership of its DNN with high confidence. This paper presents TATTOOED, a robust and efficient DNN watermarking technique based on spread-spectrum channel coding. TATTOOED has a negligible effect on the performance of the DNN model and is robust against several state-of-the-art mechanisms used to remove watermarks from DNNs. Our results show that TATTOOED is robust to such removal techniques even in extreme scenarios. For example, if the removal techniques such as fine-tuning and parameter pruning change as much as 99 parameters, the TATTOOED watermark is still present in full in the DNN model and ensures ownership verification.

READ FULL TEXT
research
11/19/2019

A novel method for identifying the deep neural network model with the Serial Number

Deep neural network (DNN) with the state of art performance has emerged ...
research
08/13/2020

Deep-Lock: Secure Authorization for Deep Neural Networks

Trained Deep Neural Network (DNN) models are considered valuable Intelle...
research
08/11/2021

SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)

Deep Neural Network (DNN) watermarking is a method for provenance verifi...
research
05/30/2018

Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks

Deep neural networks (DNNs) provide excellent performance across a wide ...
research
07/07/2021

Immunization of Pruning Attack in DNN Watermarking Using Constant Weight Code

To ensure protection of the intellectual property rights of DNN models, ...
research
09/04/2023

Safe and Robust Watermark Injection with a Single OoD Image

Training a high-performance deep neural network requires large amounts o...
research
12/28/2020

Spread-Transform Dither Modulation Watermarking of Deep Neural Network

DNN watermarking is receiving an increasing attention as a suitable mean...

Please sign up or login with your details

Forgot password? Click here to reset