Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Reducing Line Loss01:18

Reducing Line Loss

176
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...
176
Downsampling01:20

Downsampling

194
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
194
Deconvolution01:20

Deconvolution

198
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
198
Convolution Properties II01:17

Convolution Properties II

239
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
239
Convolution Properties I01:20

Convolution Properties I

188
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
188
Upsampling01:22

Upsampling

266
Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...
266

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
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

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

Journal of imaging·2022

相关实验视频

Updated: Jul 25, 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

585

在微调模型中使用恒定重量代码对卷积层的白框水印.

Minoru Kuribayashi1, Tatsuya Yasui1, Asad Malik2

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

Journal of imaging
|June 27, 2023
PubMed
概括

这项研究通过在任何卷积层中嵌入水标来增强深度神经网络 (DNN) 水标,而不仅仅是完全连接的水标. 非可真菌代币确保了DNN知识产权保护的水标完整性和创建时间验证.

科学领域:

  • 人工智能的人工智能
  • 计算机科学 计算机科学
  • 网络安全 网络安全

背景情况:

  • 深度神经网络 (DNN) 水印保护知识产权,但面临诸如神经元修剪和有限的嵌入层等挑战.
  • 现有的方法往往侧重于对再培训和微调的强度,水印通常只嵌入完全连接的层.

研究的目的:

  • 扩展DNN水印技术,适用于DNN模型中的任何卷积层.
  • 利用提取的重量参数进行统计分析,开发出强大的水印探测器.
  • 利用非真菌代币来增强水印安全性和时间印.

主要方法:

  • 开发了一种扩展的DNN水印方法,适用于卷积层.
  • 基于对重量参数的统计分析设计了一个水印探测器.
  • 集成的非真菌代币技术,以防止水印覆盖和记录创建时间.

主要成果:

  • 拟议的方法成功地将水印嵌入到卷积层中,扩大了适用于完全连接的层之外的应用范围.
  • 统计水印检测器有效地识别了水印的存在.
  • 非真菌代币提供了一种安全和可验证的方法来保护DNN水印.

结论:

关键词:
在 DNN 水印中使用 DNN 水印.常量重量代码 常量重量代码检测 检测 检测 检测 检测微调模型的微调模型.非可变性代币是非可变性代币.

更多相关视频

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.2K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K

相关实验视频

Last Updated: Jul 25, 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

585
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.2K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K
  • 这项研究通过使水印嵌入到任何卷积层来显著推进DNN水印.
  • 统计分析和非真菌代币的整合为保护DNN模型提供了更强大,更安全的解决方案.
  • 这些发现有助于保障人工智能领域的知识产权.