SRS DeepFake Detection by Deep Learning Methods

Deepfake technology refers to the creation of fake content by means of artificial intelligence. Fake content such as fake faces, fake audio, fake news etc. are spreading nowadays. Deepfakes are easier to create due to the use of smartphones and AI applications. Those deepfakes are a threat to society as they disrupt people’s privacy, defamation of celebrities/politicians etc. Deepfakes can be created by swapping someone’s face and/or swapping the speech of the person etc. Web applications like DeepFaceLab, FaceSwap and mobile applications like Reface, FaceMagic etc. are used to swap the faces of the target person with the source. Similarly, voices can be swapped or cloned by means of many applications like wav2lip, Reface etc. In this project, our goal is to detect those deepfakes by deep learning techniques from the given dataset that will be provided by the
supervisor.

Scope of Project DeepFake Detection by Deep Learning Methods :

Project scope is the part of project planning that involves determining and documenting a list of specific project  goals, deliverables, tasks, costs and deadlines. Defining the project scope involves adopting a clear vision and an agreement on the outcomes of the project. This allows each milestone of the project to stay on target

Functional and Non Functional Requirements of DeepFake Detection by Deep Learning Methods:

Functional Requirements of DeepFake Detection by Deep Learning Methods:

A functional requirement shows that what the system must do what services the system present to users. It describes a software system or its component. A function is nothing but inputs to the software system, its behavior, and outputs

NON-FUNCTIONAL REQUIREMENTS DeepFake Detection by Deep Learning Methods:

• Application is user friendly.
• Application Perform fast manipulation and calculations.
• Application is adaptable.
• Application will be able to work on all types of operating systems.
• Application will be capable to handle multi user activities simultaneously.
• There will be back up system to face any problem in system
• All the options should be learning friendly I.e. member could easily understand what that option will do if he clicked on it.
• Response Time is very awesome.

Some others are:

• Accessibility
• Maintainability
•  Fault Tolerance.
• Security
• Robustnes

Use Case Diagram of DeepFake Detection by Deep Learning Methods

a use case diagram can summarize the details of your system’s users   and their interactions with the system. Scenarios in which your system or application interacts with organizations, people, or external systems. Goals that your system or application helps those entities achieve

Usage Scenarios DeepFake Detection by Deep Learning Methods:

A brief user story explaining who is using the system and what they are trying to accomplish. A Scenario is made up of a number of simple, discrete steps that are designated as being performed by either the System or a  User.

ADOPTED METHODOLOGY for DeepFake Detection by Deep Learning Methods:

The adopted methodology for this project is vu process model. Vu process model is a combination of water-fall model and spiral model. This combination has many advantages. This model has high risk analysis so avoidance of risk would be achieved. This model is easy to understand and use. Now first we will discuss the Water-fall model.

Work Plan of DeepFake Detection by Deep Learning Methods:

Work plan

for complete srs contact us

watsapp: 03469806607