SUMMARY OF THE PROJECT:

NAME: ____________________________

TITLE OF THE PROJECT: “DEFECT DETECTION IN NETWORK USING MACHINE

PROBLEM STATEMENT OF THE PROJECT:

One of the main efficiency drawbacks of the most existing ABE schemes is that decryption is

expensive for resource-limited devices due to pairing operations, and the number of pairing

operations required to decrypt a cipher text grows with the complexity of the access policy.

The above observation motivates us to study ABE with verifiable outsourced

decryption in this thesis work. Here emphasized that an ABE scheme with secure outsourced

decryption does not necessarily guarantee verifiability (i.e., correctness of the transformation

done by the cloud server).

WHY IS THE PARTICULAR TOPIC CHOSEN?

I want to study about multiple platform background based on strength of technology.

To analysis about python and Machine Learning techniques.

To improve my algorithms knowledge for machine learning. From this topic to understand for
internal and external behavior for machine learning unsupervised dataset.

From this topic to understand following algorithms like.

 Decision tree algorithm

1
  KNN algorithm
 Multilayer perceptron algorithm
 Naive Bayes algorithm
 Random forest algorithm

OBJECTIVE OF THE PROJECT:

Cloud network monitoring data is dynamic and distributed. Signals to monitor the cloud can

appear, disappear or change their importance and clarity over time. Machine learning (ML)

models tuned to a given data set can therefore quickly become inadequate. A model might be

highly accurate at one point in time but may lose its accuracy at a later time due to changes in

input data and their features. Distributed learning with dynamic model selection is therefore

often required. Under such selection, poorly performing models (although aggressively tuned for

the prior data) are retired or put on standby while new or standby models are brought in.

GOAL OF THE PROJECT:

The well-known method of Ensemble ML (EML) may potentially be applied to improve the

overall accuracy of a family of ML models. Unfortunately, EML has several disadvantages,

including the need for continuous training, excessive computational resources, and requirement

for large training datasets, high risks of over fitting, and a time-consuming model-building

process. In this paper, we propose a novel cloud methodology for automatic ML model selection

and tuning that automates model building and selection and is competitive with existing

methods. We use unsupervised learning to better explore the data space before the generation of

targeted supervised learning models in an automated fashion. In particular, we create Cloud

DevOps architecture for auto tuning and selection based on container orchestration and

2
messaging between containers, and take advantage of a new auto scaling method to dynamically

create and evaluate instantiations of ML algorithms. The proposed methodology and tool are

demonstrated on cloud network security datasets.

METHODOLOGY:

Methodology is the stage of the project when the theoretical design is turned out into a working

system. Thus it can be considered to be the most critical stage in achieving a successful new

system and in giving the user, confidence that the new system will work and be effective.

The methodology stage involves careful planning, investigation of the existing system and it’s

constraints on methodology, designing of methods to achieve changeover and evaluation of

changeover methods.

MAIN METHODOLOGY:-

1. Cloud Platform:

ML framework lies in its ability of maintaining lightweight and powerful accountability that

combines aspects of access control, usage control and authentication. By means of the ML, data

owners can track not only whether or not the service-level agreements are being honored, but

also enforce access and usage control rules as needed.

2. DISTINCT MODE FOR AUDITING:

Push mode:

The push mode refers to logs being periodically sent to the data owner or stakeholder.

Pull mode:

Pull mode refers to an alternative approach whereby the user

(Or another authorized party) can retrieve the logs as needed.

3
3. LOGGING AND TUNING TECHNIQUES:

1. The logging should be decentralized in order to adapt to the dynamic nature of the cloud.

More specifically, log files should be tightly bounded with the corresponding data being

controlled, and require minimal infrastructural support from any server In ML Algorithms.

2. Every access to the user’s data should be correctly and automatically logged. This requires

integrated techniques to authenticate the entity that accesses the data, verify, and record the

actual operations on the data as well as the time that the data have been accessed.

3. Log files should be reliable and tamper proof to avoid illegal insertion, deletion, and

modification by malicious parties. Recovery mechanisms are also desirable to restore damaged

log files caused by technical problems.

4. Log files should be sent back to their data owners periodically to inform them of the current

usage of their data. More importantly, log files should be retrievable anytime by their data

owners when needed regardless the location where the files are stored.

5. The proposed technique should not intrusively monitor data recipients’ systems, nor it should

introduce heavy communication and computation overhead, which otherwise will hinder its

feasibility and adoption in practice.

4
4. MAJOR COMPONENTS OF ML:

There are two major components of the ML, the first being the Auto selection, and the second

being the Auto Tuning.

The logger is strongly coupled with user’s data (either single or multiple data items). Its main

tasks include automatically logging access to data items that it contains, encrypting the log

record using the public key of the content owner, and periodically sending them to the log

harmonizer. It may also be configured to ensure that access and usage control policies associated

with the data are honored. For example, a data owner can specify that user X is only allowed to

view but not to modify the data. The auto selection will control the data access even after it is

downloaded by user X. The auto tuning forms the central component which allows the user

access to the log files. The auto selection is responsible for auditing.

HARDWARE AND SOFTWARE TO BE USED:

H/W SYSTEM CONFIGURATION:-

Processor - Pentium –IV

Hard Disk - 80 GB

S/W SYSTEM CONFIGURATION:-

 Operating System : Windows8/10

5
  Application Server : Glassfish

 Front End : HTML5/CSS

 Scripts : JavaScript and JQuery.

 Server side Script : Java, Python with ML.

 Database : MySQL 5.0

TESTING TECHNOLOGIES:

Used in selenium python technologies for Machine Learning algorithm. Major powerful
automation testing in industry for Selenium with Python. I used this project Selenium Python
Technologies.

WHAT CONTRIBUTION WOULD THE PROJECT MAKE?

 We propose a novel automatic and enforceable logging mechanism in the cloud.

 Our proposed architecture is platform independent and highly decentralized, in

that it does not require any dedicated authentication or storage system in place.

 We go beyond traditional access control in that we provide a certain degree of

usage control for the protected data after these are delivered to the receiver.

 We conduct experiments on a real cloud test bed. The results demonstrate the

efficiency, scalability, and granularity of our approach. We also provide a

detailed security analysis and discuss the reliability and strength of our

architecture.