# Spy-Watermark: Robust Invisible Watermarking for Backdoor Attack

arXiv: https://arxiv.org/abs/2401.02031 · HTML: https://mlsanity.com/paper/2401.02031/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 24 references that are in the map.
- First posted on arXiv 4 Jan 2024.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [Invisible Backdoor Attack with Sample-Specific Triggers](https://mlsanity.com/paper/2012.03816/) (2020)
- [Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks](https://mlsanity.com/paper/2007.02343/) (2020)
- [A new Backdoor Attack in CNNs by training set corruption without label poisoning](https://mlsanity.com/paper/1902.11237/) (2019)
- [Rethinking the Backdoor Attacks' Triggers: A Frequency Perspective](https://mlsanity.com/paper/2104.03413/) (2021)
- [Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation](https://mlsanity.com/paper/1808.10307/) (2018)
- [Adversarial Camouflage: Hiding Physical-World Attacks with Natural Styles](https://mlsanity.com/paper/2003.08757/) (2020)
- [Backdoor Attack against Speaker Verification](https://mlsanity.com/paper/2010.11607/) (2020)
- [FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysis](https://mlsanity.com/paper/2112.01148/) (2021)
- [Poison Ink: Robust and Invisible Backdoor Attack](https://mlsanity.com/paper/2108.02488/) (2021)
- [An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defences](https://mlsanity.com/paper/2111.08429/) (2021)
- [Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class](https://mlsanity.com/paper/2210.09194/) (2022)
- [Backdoor Attack through Frequency Domain](https://mlsanity.com/paper/2111.10991/) (2021)

## Built on by (most cited first, 7 of 7)

- [GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian Splatting](https://mlsanity.com/paper/2410.23718/) (2024)
- [Protecting NeRFs' Copyright via Plug-And-Play Watermarking Base Model](https://mlsanity.com/paper/2407.07735/) (2024)
- [Geometry Cloak: Preventing TGS-based 3D Reconstruction from Copyrighted Images](https://mlsanity.com/paper/2410.22705/) (2024)
- [MarkSplatter: Generalizable Watermarking for 3D Gaussian Splatting Model via Splatter Image Structure](https://mlsanity.com/paper/2509.00757/) (2025)
- [GeometrySticker: Enabling Ownership Claim of Recolorized Neural Radiance Fields](https://mlsanity.com/paper/2407.13390/) (2024)
- [GaussianSeal: Rooting Adaptive Watermarks for 3D Gaussian Generation Model](https://mlsanity.com/paper/2503.00531/) (2025)
- [When Harmful Content Gets Camouflaged: Unveiling Perception Failure of LVLMs with CamHarmTI](https://mlsanity.com/paper/2512.03087/) (2025)

## Abstract (arXiv)

Backdoor attack aims to deceive a victim model when facing backdoor instances while maintaining its performance on benign data. Current methods use manual patterns or special perturbations as triggers, while they often overlook the robustness against data corruption, making backdoor attacks easy to defend in practice. To address this issue, we propose a novel backdoor attack method named Spy-Watermark, which remains effective when facing data collapse and backdoor defense. Therein, we introduce a learnable watermark embedded in the latent domain of images, serving as the trigger. Then, we search for a watermark that can withstand collapse during image decoding, cooperating with several anti-collapse operations to further enhance the resilience of our trigger against data corruption. Extensive experiments are conducted on CIFAR10, GTSRB, and ImageNet datasets, demonstrating that Spy-Watermark overtakes ten state-of-the-art methods in terms of robustness and stealthiness.