Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Mar 12, 2026

Picoinjection of Microfluidic Drops Without Metal Electrodes

Picoinjection of Microfluidic Drops Without Metal Electrodes

Published on: April 18, 2014

Safe and Robust Watermark Injection with a Single OoD Image.

Shuyang Yu¹, Junyuan Hong^1,2, Haobo Zhang¹

¹Department of Computer Science and Engineering, Michigan State University.

... International Conference on Learning Representations

|March 11, 2026

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Primary Cilia as Integrative Hubs of Metabolic Signaling in Type 2 Diabetes: Inter-Organ Evidence From Central, Peripheral, and Pancreatic Islet Tissues.

Journal of cellular physiology·2026

Same author

Change in diversity patterns of fish by cascade dams: comprehensive dataset of eDNA and traditional evidence from the Jinsha River.

Journal of environmental management·2026

Same author

A pan-cancer single-cell atlas uncovers the role of sex hormones and chromosomes in sex-divergent reprogramming of the tumor microenvironment.

Cell communication and signaling : CCS·2026

Same author

Mechanotransduction in glioma stem cell fate determination: from niche mechanics to therapeutic vulnerability and state plasticity.

Frontiers in cell and developmental biology·2026

Same author

DTI-ALPS and subcortical structural-functional coupling mediate the impact of sleep quality on working memory in insomnia disorder.

Psychological medicine·2026

Same author

A Fine-grained Spatiotemporal ECoG Dataset during Speech Perception in Tonal Language.

Scientific data·2026

This study introduces a novel deep neural network watermarking method using a single out-of-distribution image. This technique offers robust intellectual property protection against common removal attacks without needing training data.

Area of Science:

Artificial Intelligence
Computer Science
Machine Learning Security

Background:

Deep neural networks (DNNs) demand significant data and computational power.
Protecting intellectual property (IP) for DNNs is a critical challenge.
Existing watermarking methods often rely on training data poisoning, raising privacy concerns and lacking robustness against model modifications.

Purpose of the Study:

To propose a safe and robust backdoor-based watermarking technique for DNNs.
To develop a method for IP verification independent of training data.
To enhance watermark resilience against common removal attacks.

Main Methods:

A novel watermarking technique leveraging a single out-of-distribution (OoD) image as a secret key.

More Related Videos

Quantifying Intermembrane Distances with Serial Image Dilations

Quantifying Intermembrane Distances with Serial Image Dilations

Published on: September 28, 2018

A New Best Practice for Validating Tail Vein Injections in Rat with Near-infrared-Labeled Agents

A New Best Practice for Validating Tail Vein Injections in Rat with Near-infrared-Labeled Agents

Published on: April 19, 2019

Related Experiment Videos

Last Updated: Mar 12, 2026

Picoinjection of Microfluidic Drops Without Metal Electrodes

Picoinjection of Microfluidic Drops Without Metal Electrodes

Published on: April 18, 2014

Quantifying Intermembrane Distances with Serial Image Dilations

Quantifying Intermembrane Distances with Serial Image Dilations

Published on: September 28, 2018

A New Best Practice for Validating Tail Vein Injections in Rat with Near-infrared-Labeled Agents

A New Best Practice for Validating Tail Vein Injections in Rat with Near-infrared-Labeled Agents

Published on: April 19, 2019

Injection of backdoor triggers using the OoD image's diverse knowledge.

Inducing robustness through random perturbation of model parameters during watermark injection.

Main Results:

The proposed method is time- and sample-efficient, requiring no access to training data.
Demonstrated robustness against common watermark removal attacks like fine-tuning, pruning, and model extraction.
Effective IP verification through the unique secret key derived from the OoD image.

Conclusions:

The developed watermarking approach provides a secure and resilient solution for DNN intellectual property protection.
The method overcomes the limitations of traditional watermarking techniques by eliminating the need for training data and enhancing robustness.
This technique offers a practical and efficient way to safeguard commercial ownership of deep learning models.