当前位置:网站首页>Work summary of the week from November 22 to 28, 2021
Work summary of the week from November 22 to 28, 2021
2022-06-12 07:47:00 【Jace Lee】
List of articles
〇、 explain
Recent work involves technical details , To prevent a very small probability of peer leakage , The summary of work details will not be made public , Only brief work contents are recorded here .
One 、 Job content
1、 According to the idea that popped up last week , Thinking and designing a system , The actual simulation is feasible . But the robustness is not very good for different systems . But for DOLFE The physical system given in this paper can work perfectly .
2、 Then the simulation of this idea , In the same file system , Several other algorithm simulations are written for comparison :
DFFWM Classic security algorithm
NRD Security algorithms
DOLFE No secure algorithm
DOLFE Security algorithms
DOLFE Improved security algorithm
3、 About the innovation of this idea , There are the following considerations :
- Under the new fusion framework, the robustness of attacks is realized ;
- The system under consideration can be a cloud system , That is, the terminal equipment has no computing capacity , All fusion and security are provided by the fusion center ( Cloud ) To complete ;
- At the same time, it does not increase the communication pressure at all ( Compared with other fusion and security algorithm systems , Information other than state estimation and covariance needs to be transmitted . This has to be compared with a literature ).
- MSE Better than the comparison algorithm , A more stable
- Add a new attack model , Can consider both offset attack and zero mean Gaussian attack .
4、 Inferiority
- It is not effective against extremely concealed attacks ( Equivalent to a state without a secure algorithm , No attack detected )
- You need to set a threshold , But compared to the NRD for , There are fewer thresholds to set .
Two 、 Experience
Thick and thin hair .
3、 ... and 、 What to do next
1、 Further refine the idea , Make a framework .
2、 Get ready for the opening .
边栏推荐
- Summary of machine learning + pattern recognition learning (VI) -- feature selection and feature extraction
- 20220526 yolov1-v5
- [yolo-v5 learning notes]
- Knife4j first use
- 移动端、安卓、IOS兼容性面试题
- Arrangement of statistical learning knowledge points -- maximum likelihood estimation (MLE) and maximum a posteriori probability (map)
- Gradient epic memory for continuous learning
- Process terminated
- Voice assistant - Measurement Indicators
- Golang quickly generates model and queryset of database tables
猜你喜欢

Voice assistant - Multi round conversation (theory and concept)

Arrangement of statistical learning knowledge points gradient descent, least square method, Newton method

Classic paper review: palette based photo retrieval

Hongmeng OS first training

Voice assistant - Qu - single entity recall

Topic 1 Single_ Cell_ analysis(2)

2022 electrician (elementary) examination question bank and simulation examination

Logistic regression

Summary of machine learning + pattern recognition learning (IV) -- decision tree

In depth learning - overview of image classification related models
随机推荐
ECMAScript6面试题
What is a good recommendation system?
解决逆向工程Mapper重复问题
R language uses the sum function of epidisplay package to calculate the descriptive statistical summary information of the specified variables in dataframe under different grouping variables, visualiz
Summary of machine learning + pattern recognition learning (VI) -- feature selection and feature extraction
R语言使用neuralnet包构建神经网络回归模型(前馈神经网络回归模型),计算模型在测试集上的MSE值(均方误差)
Ecmascript6 interview questions
Modelants II
Chapter V - message authentication and digital signature
R语言dplyr包mutate_at函数和one_of函数将dataframe数据中指定数据列(通过向量指定)的数据类型转化为因子类型
Personalized federated learning with Moreau envelopes
LeetCode笔记:Weekly Contest 296
20220526 yolov1-v5
Golang 快速生成数据库表的 model 和 queryset
xshell安装
Voice assistant - Qu - single entity recall
Summary of machine learning + pattern recognition learning (IV) -- decision tree
Modelarts培训任务1
LeetCode笔记:Weekly Contest 295
Voice assistant - Introduction and interaction process