Blockchain and Machine Learning used in communications and networking devices

In recent years the amount of data needed to be passed through end devices has been increasing drastically. The systems and applications being used have only gotten more complicated however there is one flaw that cybersecurity analysts have been trying to solve, Security. With the advent of cryptocurrency, a solution might’ve been discovered. This being blockchain, which is used quite frequently in cryptocurrency. “Blockchain is essentially a distributed ledger, which is maintained by the network participants in a logical Peer-to-Peer (P2P) network. It establishes a trust paradigm among people and machines and enables applications to be operated without any central controller or any intermediary”.[1] However the system still needs to be trained to provide a strong security, which is why the idea of running blockchain in conjunction with machine learning is an idea that is currently being used.

 

Fig. 1 overview of the integration of blockchain and machine learning in communications and networking

 

 

Although machine learning and blockchain seem promising for the use of communications and networking. It doesn’t come without its own set of problems. The article titled blockchain and machine learning for communications and networking systems, describes these problems as “including resource management, big data processing, scalability, security and privacy. Big data processing, which makes the design and analysis of the integration of blockchain and ML even more difficult, should be well addressed in future research. Particularly, unlike traditional centralized technologies, a fundamental challenge of the integration of blockchain and ML is how to deal with the scalability issue, especially for large-scale complex systems”.[1]

 

Generally there are three different types of blockchains that can be used, public, private and consortium blockchain. Public blockchain is basically permission less anyone can join and all transactions made are open. To make a new blockchain you would need to computationally solve very complex math problems which disincentives hacking. The openness of public makes it a security concern however. Private blockchains unlike public blockchains are private and need permissions to join it. It allows rules to be applied to it however since it’s managed by an organization the organization could tamper with the blockchain or make it rollback. Consortium blockchains are operated by pre-selected nodes. This means that it has values of both private and public blockchains. Instead of it being operated by all the nodes, several nodes can be changed. This is to make it both more scalable and add privacy to it. However it would take several participants to come to a consensus for the data to be tampered.

 

What is exactly machine learning and why should it be used in conjunction with blockchain? Coined by Samuel in 1959 it means “the field of study that gives computers the ability to learn without being explicitly programmed”[1].  There are 3 types of machine learning like blockchain, they are supervised, unsupervised, and semi supervised learning. Supervised learning involves labeling datasets to help the machine learn. It is great in that it can be used in almost any kind of field. However labeling each dataset can be quite time consuming. Unsupervised learning doesn’t use labels but instead ranks the datasets according to their similarities using a similarity measure like cosine similarity or euclidean distance. It is useful in that it isn’t time consuming however it isn’t as accurate as supervised learning. Semi supervised just labels a few datasets this advantageous in that it allows the machine to learn more accurately and isn’t as time consuming as supervised learning. 

 

By utilizing these systems in conjunction, the security of network systems is improved. However although scalability, resource management and big data processing could cause problems. This is offset by the benefits machine learning and blockchain offer. By using the secure system of blockchain and allowing machine learning to adapt to certain security flaws. A pretty secure system could be made from these 2 systems.

 

References:

[1] Blockchain and Machine Learning for Communications and Networking Systems by Yiming Liu, F. Richard Yu, Xi Li, Hong Ji,  Victor C. M. Leung 

https://ieeexplore-ieee-org.ezproxy1.lib.asu.edu/stamp/stamp.jsp?tp=&arnumber=9007406&tag=1

Comments

  1. EricaJanuary 5, 2022 at 9:59 AM

    Bao,
    Very nice work this past semester. I love to see all the application-driven assignments and really thorough summaries. Hope your holiday season was restful!
    Best,
    Erica

    ReplyDelete

Post a Comment

Popular posts from this blog

#7 Sklearn - Python Package - Linear Regression (Part 2)

Image
In this week, I continue working on Linear Regression project about predicting house pricing in Washington state. Comparing to the previous journal, this one is elaborated with more explanation and steps.  Linear Regression algorithm generally means we will use a straight line to display the relationship between 2 variables (dependent and independent variables, or features and target). In other words, we will use this algorithm to predict the output (dependent variables) bases on the input (independent variable). For packages in needed, we will import Linear Regression from sklearn.linear_model (using for creating linear regression and making prediction), train_test_split from sklearn.model_selection (using for splitting out data into 4 subset), import metrics from sklearn (using for evaluating accuracy of our model), import matplotlib.pyplot (using for visualizing data), and %matplotlib.inline for displaying the graph interactively in jupyter notebook. I downloaded dataset from Ka...
Read more

#3 Project Progress: Import and Clean the Data in Python

Image
I am so excited to share with you about my first project in Python related to Data Science. In order to complete this project, first of all, we need to import the data. Jupyter notebook is a interactive computing notebook environment, that is came with Anaconda - a Python distribution for scientific computing. We will run our code on this notebook. We will use read_csv() method in pandas package to read the csv files. My file here is Data.csv, that I download from Kaggle ( TMDB 5000 Movie Dataset | Kaggle ). df.head() uses for printing some head rows of data. df.shape() uses for printing the shape of data, you can see in this data set, we have 8403 rows and 20 different features.  After importing the data, we need to clean them to make sure we won't mess them up when we manipulate to build a model. We have total 20 features here but we won't use them all. So, we need to decide what features are important and what are not. Because I want to build a content-based movie recommenda...
Read more

#6 Sklearn - Python package - Linear Regression

Image
In this week, I am learning an algorithm in sklearn package (python) names Linear Regression. Linear Regression "is a linear approach for modelling the relationship between a scalar response and one or more explanatory variable (also known as dependent and independent variables). In these pictures below, I was using Linear Regression to predict the house pricing in Washington State. I have also exposed the new graphic packages are seaborn and matplot, I won't plan to inquire too much in these, but I found it's helpful to visualize the data. To me, the best way to learn something is practicing and working through specific project. That's why I always try to find something related to what I want to learn then start it. It looks pretty messy now, but I will give an update soon in next week after I elaborate my code beautifully. 
Read more