# DLOVE: A new Security Evaluation Tool for Deep Learning Based Watermarking Techniques

arXiv: https://arxiv.org/abs/2407.06552 · HTML: https://mlsanity.com/paper/2407.06552/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 53 references that are in the map.
- First posted on arXiv 9 Jul 2024.

## Builds on (most cited first, 25 of 25)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Practical Black-Box Attacks against Machine Learning](https://mlsanity.com/paper/1602.02697/) (2016)
- [The Limitations of Deep Learning in Adversarial Settings](https://mlsanity.com/paper/1511.07528/) (2015)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [Delving into Transferable Adversarial Examples and Black-box Attacks](https://mlsanity.com/paper/1611.02770/) (2016)
- [Black-box Adversarial Attacks with Limited Queries and Information](https://mlsanity.com/paper/1804.08598/) (2018)
- [Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples](https://mlsanity.com/paper/1605.07277/) (2016)
- [HiDDeN: Hiding Data With Deep Networks](https://mlsanity.com/paper/1807.09937/) (2018)
- [Simple Black-box Adversarial Attacks](https://mlsanity.com/paper/1905.07121/) (2019)
- [MBRS : Enhancing Robustness of DNN-based Watermarking by Mini-Batch of Real and Simulated JPEG Compression](https://mlsanity.com/paper/2108.08211/) (2021)
- [SiT: Self-supervised vIsion Transformer](https://mlsanity.com/paper/2104.03602/) (2021)
- [Distortion Agnostic Deep Watermarking](https://mlsanity.com/paper/2001.04580/) (2020)
- [ReDMark: Framework for Residual Diffusion Watermarking on Deep Networks](https://mlsanity.com/paper/1810.07248/) (2018)
- [An Automated and Robust Image Watermarking Scheme Based on Deep Neural Networks](https://mlsanity.com/paper/2007.02460/) (2020)
- [Erase and Repair: An Efficient Box-Free Removal Attack on High-Capacity Deep Hiding](https://mlsanity.com/paper/2308.01512/) (2023)
- [Deep learning is a good steganalysis tool when embedding key is reused for different images, even if there is a cover source-mismatch](https://mlsanity.com/paper/1511.04855/) (2015)
- [PixelSteganalysis: Pixel-wise Hidden Information Removal with Low Visual Degradation](https://mlsanity.com/paper/1902.10905/) (2019)
- [Destruction of Image Steganography using Generative Adversarial Networks](https://mlsanity.com/paper/1912.10070/) (2019)

## Abstract (arXiv)

Recent developments in Deep Neural Network (DNN) based watermarking techniques have shown remarkable performance. The state-of-the-art DNN-based techniques not only surpass the robustness of classical watermarking techniques but also show their robustness against many image manipulation techniques. In this paper, we performed a detailed security analysis of different DNN-based watermarking techniques. We propose a new class of attack called the Deep Learning-based OVErwriting (DLOVE) attack, which leverages adversarial machine learning and overwrites the original embedded watermark with a targeted watermark in a watermarked image. To the best of our knowledge, this attack is the first of its kind. We have considered scenarios where watermarks are used to devise and formulate an adversarial attack in white box and black box settings. To show adaptability and efficiency, we launch our DLOVE attack analysis on seven different watermarking techniques, HiDDeN, ReDMark, PIMoG, Stegastamp, Aparecium, Distortion Agostic Deep Watermarking and Hiding Images in an Image. All these techniques use different approaches to create imperceptible watermarked images. Our attack analysis on these watermarking techniques with various constraints highlights the vulnerabilities of DNN-based watermarking. Extensive experimental results validate the capabilities of DLOVE. We propose DLOVE as a benchmark security analysis tool to test the robustness of future deep learning-based watermarking techniques.