Securing Data Using DES, RSA, AES And LSB Steganography

ABSTRACT:

Data security is the main concern in different types of applications from data storing in clouds to sending messages using chat. In order to provide security for data in the cloud, there are many types of techniques which are already proposed like AES, DES, RSA but in existing methods, most of the time only a single type of encryption was used either AES, OR DES, OR RSA based on user requirement but in this system main problem is each encryption is done using encryption keys if these keys are exposed in any case entire data is lost so we need an effective method which can provide more security so in this project hybrid cryptography is used where existing encryption methods are used but three methods will be used. When the user uploads data will split into three parts and the first part will be encrypted using AES, the second part will be encrypted using DES, the third part will be encrypted using RSA  and these three encrypted files will be stored in the cloud and keys used for AES, DES and RSA are stored in the image using LSB steganography when users want to download total data from cloud-first keys should be retrieved from the image and these keys are used for decrypting data again by using AES, DES and RSA and final data is combined and stored in the file. This method provides more security for data.

OBJECTIVE:

Data security is the main issue in cloud data management there is a chance of developing effective methods like hybrid cryptography for improving security. In this project, AES, DES, RSA is used along with LSB.

INTRODUCTION:

 Cloud is playing important role in data management and another type of service that provides a secure way of data handling and remote data accessing where users from anywhere can use the cloud for data access. As the cloud is a third-party application where data uploaded by users must provide security features to reduce risks from data attacks in order to do that encryption techniques here used like AES, DES, and RSA.

EXISTING SYSTEM:

In the existing system cloud used to use any one of the encryption technique and keys verification is done using the identity of the user. Based on application requirements different encryption techniques are used.

DISADVANTAGES:

Only single encryption techniques are used and keys are not managed effectively there are chances of leakage of keys. 

PROPOSED SYSTEM:

In order to improve security for cloud data compare to existing techniques where keys are shared security between users new hybrid cryptography technique is proposed where three types of encryption are used AES, DES, and RSA and the LSB steganography technique is used for secure key sharing.

ADVANTAGES:

Data is split into three parts and each part is encrypted using one encryption technique and keys are shared securely by embedding in the image.

SOFTWARE REQUIREMENTS: 

  • Operating system: Windows 7.
  • Coding Language: python
  • Tool: anaconda, visual studio code
  • Database: SQL lite

Drowsiness Detection using OpenCV

Abstract:

The new way of security system which will be discussed in this project is based on machine learning and artificial intelligence. Passenger security is the main concern of the vehicle’s designers where most of the accidents are caused due to drowsiness and fatigued driving in order to provide better security for saving lives of passengers airbag are designed but this method is useful after an accident is an accord. But the main problem is still we see many accidents happening and many of them are losing their lives. In this project we are using the OpenCV library for image processing and giving input as user live video and training data to detect if the person in the video is closing eyes or showing any symptoms of drowsiness and fatigue then the application will verify with trained data and detect drowsiness and raise an alarm which will alert the driver.

Existing system:

There are various methods like detecting objects which are near to vehicle and front and rear cameras for detecting vehicles approaching near to vehicle and airbag system which can save lives after an accident is accorded.

Disadvantages:

Most of the existing systems use external factors and inform the user about the problem and save users after an accident is accord but from research most of the accidents are due to faults in users like drowsiness, sleeping while driving.

Proposed system:

To deal with this problem and provide an effective system a drowsiness detection system can be developed which can be placed inside any vehicle which will take live video of the driver as input and compare with training data and if the driver is showing any symptoms of drowsiness system will automatically detect and raise an alarm which will alert the driver and other passengers.

Advantages:

This method will detect a problem before any problem accord and inform the driver and other passengers by raising an alarm.

In this OpenCV based machine learning techniques are used for automatic detection of drowsiness.

SOFTWARE REQUIREMENTS: 

  • Operating system: Windows 7.
  • Coding Language: python
  • Tool: anaconda, visual studio code
  • Libraries: OpenCV

Students Marks Prediction Using Linear Regression

Abstract:

Education institutions use new technologies to improve the quality of education but most of the applications which are used in colleges are related to service and development there are web applications that are helping students to take online training and tests. There are very few methods that can help teachers to know about student’s performance. Considering this problem machine learning techniques are used to predict students’ marks based on previous marks and predict results. Linear regression models are used to predict student performance and predict the next subject marks.

Problem statement:

Education institutions use web applications for training students and checking performance based on marks but there are no specific steps followed for prediction of students performance and take measures to improve performance.

Objective:

Design a machine learning model for the prediction of students marks and take measures to improve student performance. Liner regression algorithm is used to train model and prediction.

Existing system:

Researches had done work on the automation of grading techniques in which previous marks were used to give grades to students.

Algorithms like association rule mining and apriori algorithms are used for classifying students marks.

Disadvantages:

Existing methods mostly work based on marks obtained from exams.

Algorithms are used for classifying students based on marks. 

Proposed system:

Dataset of other subject marks are taken as input and data set is processed with labels and features and then test split is performed on the dataset and then machine learning model is applied to dataset then the prediction is performed.

Advantages:

Before the final marks of all subjects are evaluated prediction can be performed.

Using a machine learning process automation of marks prediction can be done. 

SOFTWARE REQUIREMENTS:

  • Operating system: Windows XP/7/10
  • Coding Language: python  
  • Development environment: anaconda, Jupiter 
  • Dataset: students marks dataset
  • IDE: Jupiter notebook

Student Coding Assignment Evaluation Using API

Abstract:

Data mining in education institutions is helping to analyze students’ details and provide an effective evaluation system in a short time. With the advancement of new technologies student’s evaluation procedure has changed from manual correction to automate process of correction and analysis. This student coding assignment evaluation system using API is designed to evaluate students coding correction process through the automation process. When a student submits an answer for a student’s question online faculty will evaluate coding by sending data to API and get results or error messages. By checking these messages faculty will give marks to students. This process is done through a web application that is developed in python programming language.  

Problem statement:

            Students assignment evaluation is a time taking process for faculty which required a manual process by checking each line of code and give marks to students. 

Objective:

            The coding evaluation process can be automated by using available code checking API’s which can be integrated into the college assignment assigning website. Using this process evaluation is completed just in a click and faculty can give marks based on result.

Existing system:

  • A manual process was used for checking assignments and evaluate results.
  • Data mining techniques were used for evaluation which uses previous coding datasets and predicts results that are not accurate.

Disadvantages:

  • Faculty must check each line of code to evaluate coding and give grading.
  • Time taken for the evaluation process is high.

Proposed system:

                        The student online coding evaluation system provides an automatic coding checking process through which faculty can assign coding assignments and get results from students and compile code in click and check result and give marks.

Advantages:

  • The entire process of assigning to evaluation is done online and coding evaluation is done in one click.
  • API is used for checking errors in code and give grading.

System requirement: 

Programing language: python

Framework: Flask

Database: MYSQL

API: for compiling code

Cyber Bullying Detection Using Machine Learning

Abstract:

Cyber bullying is the process of sending wrong messages to a person or community which causes heated debate with users. Cyberbullying is mostly seen in social networking sites where users reply to post with bullying words to threaten or insult other users. Cyberbullying is considered a misuse of technology. According to the latest survey done on all over the world data day by day, cases are increasing on cyberbullying. In order to solve this problem many natural language processing techniques are proposed by various authors which are time taking and not automatic. With the advancement of machine learning and artificial intelligence, models can be created and automatic detection can be implemented. To show this scenario live chat application is developed in python programming with multiple clients and one server and the Naive Bayes algorithm is used to train the model on a Twitter dataset and using this model live detection of cyberbullying is predicted and alert messages are shown on the chat application.

Problem statement:

       Social networking and online chatting application provide a platform for any user to share knowledge and talent but few users take this platform to threaten users with cyberbullying attacks which cause issues in using these platforms.

Objective:

    To provide a better platform for users to share knowledge on social networking sites there is a need for an effective detection system that can automate the process of cyberbullying detections and take decisions.

Existing system:

  • Techniques like unsupervised labeling methods which use N-gram, TF-IDF methods to detect cyberbullying are used which use the youtube dataset to detect attacks.
  • A support vector classifier is used to train models for detection.

Disadvantages:

         Techniques which are used in the existing system are not automated they need time to process request and update response.

           Social networking and chatting sites require automated detecting and processing methods.

Proposed system:

         Cyberbullying detection is designed using machine learning techniques. Twitter data set is collected with features and labels and mode is trained using the Naive Bayes algorithm and trained model is applied to live chatting application which has multiple clients and a single server. For each message, cyberbullying is detecting using the model and then alert messages are posted on chat boards.

Advantages:

         Cyberbullying detection process is automatic and time taken for detection is less and it works on the live environment. 

            The latest machine learning models are used for training models that are accurate.

Software Requirement:

Programming language: python

Front End GUI : tkinter

Dataset: Twitter cyberbullying dataset

Algorithm                       : Naive bayes