# Reversible Quantization Index Modulation for Static Deep Neural Network Watermarking

arXiv: https://arxiv.org/abs/2305.17879 · HTML: https://mlsanity.com/paper/2305.17879/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 31 references that are in the map.
- First posted on arXiv 29 May 2023.

## Builds on (most cited first, 9 of 9)

- [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://mlsanity.com/paper/1703.09039/) (2017)
- [Methods for Interpreting and Understanding Deep Neural Networks](https://mlsanity.com/paper/1706.07979/) (2017)
- [Embedding Watermarks into Deep Neural Networks](https://mlsanity.com/paper/1701.04082/) (2017)
- [A survey of deep neural network watermarking techniques](https://mlsanity.com/paper/2103.09274/) (2021)
- [Supervised GAN Watermarking for Intellectual Property Protection](https://mlsanity.com/paper/2209.03466/) (2022)
- [Spread-Transform Dither Modulation Watermarking of Deep Neural Network](https://mlsanity.com/paper/2012.14171/) (2020)
- [Reversible Watermarking in Deep Convolutional Neural Networks for Integrity Authentication](https://mlsanity.com/paper/2104.04268/) (2021)
- [TATTOOED: A Robust Deep Neural Network Watermarking Scheme based on Spread-Spectrum Channel Coding](https://mlsanity.com/paper/2202.06091/) (2022)
- [A Lattice-Based Embedding Method for Reversible Audio Watermarking](https://mlsanity.com/paper/2209.07066/) (2022)

## Built on by (most cited first, 1 of 1)

- [FedReverse: Multiparty Reversible Deep Neural Network Watermarking](https://mlsanity.com/paper/2312.05738/) (2023)

## Abstract (arXiv)

Static deep neural network (DNN) watermarking techniques typically employ irreversible methods to embed watermarks into the DNN model weights. However, this approach causes permanent damage to the watermarked model and fails to meet the requirements of integrity authentication. Reversible data hiding (RDH) methods offer a potential solution, but existing approaches suffer from weaknesses in terms of usability, capacity, and fidelity, hindering their practical adoption. In this paper, we propose a novel RDH-based static DNN watermarking scheme using quantization index modulation (QIM). Our scheme incorporates a novel approach based on a one-dimensional quantizer for watermark embedding. Furthermore, we design two schemes to address the challenges of integrity protection and legitimate authentication for DNNs. Through simulation results on training loss and classification accuracy, we demonstrate the feasibility and effectiveness of our proposed schemes, highlighting their superior adaptability compared to existing methods.