# Evolutionary Trigger Set Generation for DNN Black-Box Watermarking

arXiv: https://arxiv.org/abs/1906.04411 · HTML: https://mlsanity.com/paper/1906.04411/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2019.

## Built on by (most cited first, 6 of 6)

- [A Recipe for Watermarking Diffusion Models](https://mlsanity.com/paper/2303.10137/) (2023)
- [Identifying Appropriate Intellectual Property Protection Mechanisms for Machine Learning Models: A Systematization of Watermarking, Fingerprinting, Model Access, and Attacks](https://mlsanity.com/paper/2304.11285/) (2023)
- [Safe-SD: Safe and Traceable Stable Diffusion with Text Prompt Trigger for Invisible Generative Watermarking](https://mlsanity.com/paper/2407.13188/) (2024)
- [Robust Black-box Watermarking for Deep NeuralNetwork using Inverse Document Frequency](https://mlsanity.com/paper/2103.05590/) (2021)
- [RobWE: Robust Watermark Embedding for Personalized Federated Learning Model Ownership Protection](https://mlsanity.com/paper/2402.19054/) (2024)
- [Secure AI Watermarking Framework for IP Protection in Multi-Tenant Cloud Platforms](https://mlsanity.com/paper/2608.02656/) (2026)

## Abstract (arXiv)

The commercialization of deep learning creates a compelling need for intellectual property (IP) protection. Deep neural network (DNN) watermarking has been proposed as a promising tool to help model owners prove ownership and fight piracy. A popular approach of watermarking is to train a DNN to recognize images with certain textittrigger patterns. In this paper, we propose a novel evolutionary algorithm-based method to generate and optimize trigger patterns. Our method brings a siginificant reduction in false positive rates, leading to compelling proof of ownership. At the same time, it maintains the robustness of the watermark against attacks. We compare our method with the prior art and demonstrate its effectiveness on popular models and datasets.