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

Survival Tree01:19

Survival Tree

154
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
154
Reducing Line Loss01:18

Reducing Line Loss

191
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
191
Weighted Mean00:57

Weighted Mean

5.3K
While taking the arithmetic, geometric, or harmonic mean of a sample data set, equal importance is assigned to all the data points. However, all the values may not always be equally important in some data sets. An intrinsic bias might make it more important to give more weightage to specific values over others.
For example, consider the number of goals scored in the matches of a tournament. While computing the average number of goals scored in the tournament, it may be more important to...
5.3K
Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

7.0K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
7.0K
Improving Translational Accuracy02:07

Improving Translational Accuracy

11.8K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
11.8K
Residuals and Least-Squares Property01:11

Residuals and Least-Squares Property

7.8K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
7.8K

You might also read

Related Articles

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

Sort by
Same author

White Box Watermarking for Convolution Layers in Fine-Tuning Model Using the Constant Weight Code.

Journal of imaging·2023
Same author

A Throughput Request Satisfaction Method for Concurrently Communicating Multiple Hosts in Wireless Local Area Network.

Sensors (Basel, Switzerland)·2022
Same author

Group Testing with Blocks of Positives and Inhibitors.

Entropy (Basel, Switzerland)·2022
Same author

Design and Implementation of <i>SEMAR</i> IoT Server Platform with Applications.

Sensors (Basel, Switzerland)·2022
Same author

Evaluation of peak skin dose during percutaneous coronary intervention procedures: relationship with fluoroscopic pulse rate and target vessel.

Radiological physics and technology·2021
Same author

[Real-time Lens Exposure Dose Measurement Using a Scintillator with Optical Fiber Dosimeter during Cardiac Catheter Operation].

Nihon Hoshasen Gijutsu Gakkai zasshi·2020

Related Experiment Video

Updated: Sep 7, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

629

Coded DNN Watermark: Robustness against Pruning Models Using Constant Weight Code.

Tatsuya Yasui1, Takuro Tanaka1, Asad Malik2

  • 1Graduate School of Natural Science and Technology, Okayama University, Okayama 700-8530, Japan.

Journal of Imaging
|June 23, 2022
PubMed
Summary

This study introduces constant weight codes to protect Deep Neural Network (DNN) watermarking against pruning attacks. This novel channel coding approach enhances DNN model intellectual property protection by improving watermark robustness.

Keywords:
DNN modelconstant weight codefine-tuningpruning attackwatermarking

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.3K
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

866

Related Experiment Videos

Last Updated: Sep 7, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

629
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.3K
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

866

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Information Security

Background:

  • Deep Neural Network (DNN) watermarking protects intellectual property by embedding hidden information.
  • Pruning attacks threaten DNN watermarks by removing neurons, potentially deleting the watermark.
  • Existing watermarking methods lack robust defenses against pruning attacks.

Purpose of the Study:

  • To investigate a channel coding approach for enhancing DNN watermarking resilience against pruning attacks.
  • To propose a novel encoding method using constant weight codes for DNN watermarking.

Main Methods:

  • Developed a channel coding framework tailored for DNN watermarking, distinct from conventional image-based models.
  • Implemented a novel encoding strategy utilizing constant weight codes.
  • Evaluated watermark robustness against pruning attacks by adjusting codeword thresholds.

Main Results:

  • The proposed constant weight code approach effectively protects DNN watermarks against pruning.
  • The robustness of the watermark against pruning attacks can be precisely controlled.
  • Threshold settings for binary symbols in codewords directly influence attack resilience.

Conclusions:

  • Constant weight codes offer a promising solution for securing DNN watermarks against pruning.
  • This channel coding technique provides a controllable mechanism to enhance DNN model intellectual property protection.
  • Further research is needed to explore optimal encoding methods for diverse DNN watermarking scenarios.