Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

A scheme of hiding large-size image into small-size image based on FCdDNet.

PeerJ. Computer science·2024
Same author

Lossless Image Steganography Based on Invertible Neural Networks.

Entropy (Basel, Switzerland)·2022
Same author

No Superiority of High-Flexion vs Standard Total Knee Arthroplasty: An Update Meta-Analysis of Randomized Controlled Trials.

The Journal of arthroplasty·2015
Same author

When plants produce not enough or at all: metabolic engineering of flavonoids in microbial hosts.

Frontiers in plant science·2015
Same author

Synthesis and molecular structure of the 5-methoxycarbonylpentyl α-glycoside of the upstream, terminal moiety of the O-specific polysaccharide of Vibrio cholerae O1, serotype Inaba.

Molecules (Basel, Switzerland)·2015
Same author

Comparative analysis of sequence feature and expression of two heat shock cognate 70 genes in mandarin fish Siniperca chuatsi.

Gene·2015

Related Experiment Video

Updated: May 20, 2025

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

7.5K

Screen shooting resistant watermarking based on cross attention.

Lianshan Liu1, Peng Xu2, Qianwen Xue3

  • 1College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, 266590, China. liulianshan@sdust.edu.cn.

Scientific Reports
|May 16, 2025
PubMed
Summary

This study introduces a novel screen-shooting resistant watermarking (SSRW) system using advanced attention mechanisms. The new method effectively embeds watermarks to prevent data leaks from screen recordings, achieving over 95% accuracy.

Keywords:
Cross attentionDeep learningRobust watermarkingScreen-shooting

More Related Videos

A Dual Task Procedure Combined with Rapid Serial Visual Presentation to Test Attentional Blink for Nontargets
08:45

A Dual Task Procedure Combined with Rapid Serial Visual Presentation to Test Attentional Blink for Nontargets

Published on: December 5, 2014

9.1K
Using Rapid Serial Visual Presentation to Measure Set-Specific Capture, a Consequence of Distraction While Multitasking
05:58

Using Rapid Serial Visual Presentation to Measure Set-Specific Capture, a Consequence of Distraction While Multitasking

Published on: August 29, 2018

8.8K

Related Experiment Videos

Last Updated: May 20, 2025

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

7.5K
A Dual Task Procedure Combined with Rapid Serial Visual Presentation to Test Attentional Blink for Nontargets
08:45

A Dual Task Procedure Combined with Rapid Serial Visual Presentation to Test Attentional Blink for Nontargets

Published on: December 5, 2014

9.1K
Using Rapid Serial Visual Presentation to Measure Set-Specific Capture, a Consequence of Distraction While Multitasking
05:58

Using Rapid Serial Visual Presentation to Measure Set-Specific Capture, a Consequence of Distraction While Multitasking

Published on: August 29, 2018

8.8K

Area of Science:

  • Digital Forensics
  • Information Security
  • Computer Vision

Background:

  • Digital imaging devices facilitate data leaks via screen recording.
  • Screen-Shooting Resistant Watermarking (SSRW) is crucial for identifying information violations.
  • Existing Convolutional Neural Network (CNN) based methods have limitations in understanding global image context.

Purpose of the Study:

  • To develop a novel watermarking system resistant to screen recording.
  • To improve the performance and reliability of SSRW systems.
  • To address the limitations of CNNs in capturing global image features for watermarking.

Main Methods:

  • Implemented a new watermarking system utilizing multi-head and cross-attention mechanisms, replacing the CNN encoder.
  • Segmented images and watermarks into patches for positional embedding.
  • Enhanced the U-Net network structure for the decoder component.
  • Employed attention scores calculated through multi-head attention layers for watermark incorporation.

Main Results:

  • Achieved over 95% accuracy in various screen capture scenarios.
  • Demonstrated superior reliability and invisibility compared to state-of-the-art (SOTA) methods.
  • Reported excellent visual quality with average Peak Signal-to-Noise Ratio (PSNR) of 41.90 dB and Structural Similarity Index Measure (SSIM) of 0.99.

Conclusions:

  • The proposed attention-based watermarking system effectively combats data leaks from screen recordings.
  • The enhanced U-Net decoder and attention mechanisms significantly improve global image comprehension and watermarking performance.
  • The method offers a reliable and visually imperceptible solution for digital content protection against screen capture threats.