DeepAI AI Chat
Log In Sign Up

Reversible Deep Neural Network Watermarking:Matching the Floating-point Weights

by   Junren Qin, et al.

Static deep neural network (DNN) watermarking embeds watermarks into the weights of DNN model by irreversible methods, but this will cause permanent damage to watermarked model and can not meet the requirements of integrity authentication. For these reasons, reversible data hiding (RDH) seems more attractive for the copyright protection of DNNs. This paper proposes a novel RDH-based static DNN watermarking method by improving the non-reversible quantization index modulation (QIM). Targeting the floating-point weights of DNNs, the idea of our RDH method is to add a scaled quantization error back to the cover object. Two schemes are designed to realize the integrity protection and legitimate authentication of DNNs. Simulation results on training loss and classification accuracy justify the superior feasibility, effectiveness and adaptability of the proposed method over histogram shifting (HS).


page 1

page 2

page 3

page 4


FAST: DNN Training Under Variable Precision Block Floating Point with Stochastic Rounding

Block Floating Point (BFP) can efficiently support quantization for Deep...

Training Deep Neural Networks Using Posit Number System

With the increasing size of Deep Neural Network (DNN) models, the high m...

Adaptive Block Floating-Point for Analog Deep Learning Hardware

Analog mixed-signal (AMS) devices promise faster, more energy-efficient ...

Reversible Watermarking in Deep Convolutional Neural Networks for Integrity Authentication

Deep convolutional neural networks have made outstanding contributions i...

TensorQuant - A Simulation Toolbox for Deep Neural Network Quantization

Recent research implies that training and inference of deep neural netwo...

Convert, compress, correct: Three steps toward communication-efficient DNN training

In this paper, we introduce a novel algorithm, 𝖢𝖮_3, for communication-e...

A Lattice-Based Embedding Method for Reversible Audio Watermarking

Reversible audio watermarking (RAW) is a promising technique in various ...