Software Requirements Specification

(SRS) Document
Fake Social Media Profile Detection and Reporting System

1. Introduction....................................................................................

1.1 Purpose

1.2 Scope

1.3 Definitions, Acronyms, and Abbreviations

1.4 References

1.5 Overview

2. The Overall Description....................................................................

2.1 Product Perspective

2.2 Product Functions

2.3 User Characteristics

2.4 Constraints

2.5 Assumptions and Dependencies

3. External interface Requirements......................................................

3.1 User Interfaces

3.2 Hardware Interfaces

3.3 Software Interfaces

3.4 Communications Interfaces

4. System Features

5. Other Non-Functional Requirements

5.1 Performance Requirements

5.2 Capacity

5.3 Dynamic

5.4 Requirements

5.5 Quality

3.6.1 Reliability

3.6.2 Availability

3.6.3 Security

3.6.4 Maintainability

5.3 Business Rules

6. Other Requirements.....................................................................

Appendix A: Glossary

Appendix S: Analysis Models

7. Conclusion…………….

1. Introduction

1.1 Purpose

The purpose of this Software Requirements Specification (SRS) document is to

provide a detailed description of the Fake Social Media Profile Detection and
 Reporting System. This system aims to detect fake social media profiles and provide
users with a means to report suspicious accounts on various social media platforms.

1.2 Scope

The Fake Social Media Profile Detection and Reporting System will be a web-based
application accessible to users who want to verify the authenticity of social media
profiles and report potential fake accounts. The system will use advanced algorithms
and techniques to identify suspicious patterns and behaviors associated with fake
profiles on popular social media platforms.

1.3 Definitions, Acronyms, and Abbreviations

 SRS: Software Requirements Specification

 API: Application Programming Interface

1.4 References
 https://www.scirp.org/journal/paperinformation.aspx?paperid=120727
 https://ieeexplore.ieee.org/document/10150753
 https://dl.acm.org/doi/abs/10.1504/IJICS.2020.105181

1.5 Overview

n this project, we came up with a framework with which automatic detection of fake
profiles is possible and is efficient. This framework uses classification techniques like
Support Vector Machine, Nave Bayes and Decision trees to classify the profiles into
fake or genuine classes.2

2. System Overview

2.1 System Description

The Fake Social Media Profile Detection and Reporting System will be developed as a
web application. Users can input the URL or username of a social media profile they
find suspicious, and the system will analyse the profile to determine its authenticity.
The system will employ machine learning algorithms, natural language processing,
and pattern recognition techniques to identify fake profiles.

2.2 Users
 Regular Users: Individuals who want to verify the authenticity of social media
profiles.
 Administrators: System administrators responsible for managing user accounts,
reviewing reported profiles, and maintaining the system.

3. Functional Requirements

3.1 User Registration and Authentication

 Requirement 3.1.1: Users must be able to register for an account by providing a

valid email address and creating a password.
 Requirement 3.1.2: Users must be able to log in using their registered email address
and password.

3.2 Fake Profile Detection

 Requirement 3.2.1: Users can enter the URL or username of a social media profile to
initiate the fake profile detection process.
 Requirement 3.2.2: The system will analyse the profile's content, activity, and
interactions using machine learning algorithms to determine if it is fake.
 Requirement 3.2.3: The system will provide a confidence score or classification
indicating the likelihood that the profile is fake.

3.3 Reporting Functionality

 Requirement 3.3.1: Users can report profiles identified as fake by the system.
 Requirement 3.3.2: Users must provide a reason for reporting the profile, such as
suspicious activity or false information.
 Requirement 3.3.3: Reported profiles will be flagged for review by administrators.

3.4 Administrator Features

 Requirement 3.4.1: Administrators can access a dashboard displaying reported

profiles and user activity.
 Requirement 3.4.2: Administrators can review reported profiles, mark them as
confirmed fake or genuine, and take appropriate actions, such as banning fake
accounts.
 Requirement 3.4.3: Administrators can manage user accounts, including suspending
or banning users who violate the system's terms of service.

4. System Features
 Detecting and reporting fake profiles on online platforms involves various system
features and functionalities to ensure the authenticity and security of user
interactions. Here are some key system features for fake profile detection and
reporting:

1. User Profile Verification:

 Implement verification methods such as email verification or phone number
verification to confirm the authenticity of user accounts during registration.
2. Machine Learning Algorithms:
 Utilize machine learning algorithms to analyse user behaviour, profile
information, and interactions to identify patterns associated with fake profiles.
 Implement natural language processing (NLP) algorithms to analyse text
content for inconsistencies, grammar errors, or unusual language patterns.
3. Image Recognition:
 Integrate image recognition technology to detect duplicate or stolen profile
pictures across multiple user accounts.
 Use reverse image search to identify images that have been used elsewhere
on the internet.
4. Social Network Analysis:
 Apply social network analysis techniques to identify suspicious connections
and relationships between users.
 Detect unusual friend request patterns, such as rapid mass friending or mutual
connections with other suspicious accounts.
5. Behavioural Analysis:
 Monitor user behaviour, such as posting frequency, interaction patterns, and
response times, to identify automated or bot-driven accounts.
 Analyse login patterns, IP addresses, and geolocation data to detect
suspicious activity.
6. Content Analysis:
 Scan user-generated content, including profile descriptions, posts, and
comments, for inappropriate or spam content.
 Use keyword analysis and sentiment analysis to identify suspicious or
malicious content.
7. Reporting Mechanism:
 Provide users with an easy-to-use reporting mechanism to flag suspicious
profiles and content.
 Implement a reporting button or link on user profiles and posts, allowing
users to report potential fake accounts or suspicious activities.
8. Real-time Alerts:
 Send real-time alerts to users when suspicious activity is detected on their
account, prompting them to review and take action.
 Notify administrators or moderators when multiple reports are filed against a
specific user or content.
9. Community Moderation:
 Empower community moderators with tools to review reported profiles and
content efficiently.
 Allow moderators to suspend or ban suspicious accounts based on the
severity of the violation.
10. Data Privacy and Security:
 Ensure user data privacy and compliance with data protection regulations
while implementing fake profile detection mechanisms.
 Encrypt sensitive user information and implement secure protocols for data
transmission.
11. User Education:
 Educate users about the importance of verifying profiles, recognizing
suspicious behaviour, and reporting fake accounts.
 Provide guidelines and tips on how to identify potential fake profiles and
avoid scams.
12. Continuous Improvement:
 Regularly update and enhance the fake profile detection algorithms to adapt
to evolving tactics used by malicious actors.
 Analyse reported cases and feedback to improve the accuracy and efficiency
of the detection system.

By integrating these features, online platforms can create a safer and more authentic
environment for their users, reducing the prevalence of fake profiles and enhancing
overall user trust and satisfaction.

 Additional features contributing in effective and depth fake profile analysis

resulting accurate detection (Researched and added)

1. Behavioural Biometrics:
 Implement behavioural biometrics, such as mouse movement patterns and
typing behaviour, to distinguish between human users and automated bots.
2. Device Fingerprinting:
 Utilize device fingerprinting techniques to recognize and track devices used
for account creation and login, helping identify suspicious activities across
multiple accounts.
3. Two-Factor Authentication (2FA):
 Offer two-factor authentication methods, such as SMS codes, email
verification, or authenticator apps, to add an extra layer of security for user
accounts.
4. User Reputation System:
  Develop a reputation system where users are rated based on their behavior,
reliability, and the accuracy of their reports. High-reputation users can have
their reports prioritized.
5. Machine Learning Anomaly Detection:
 Train machine learning models to detect anomalous patterns in user behavior,
helping identify fake profiles based on deviations from normal user activity.
6. Social Media Integration:
 Integrate with users' social media accounts to cross-verify profile information
and connections, making it more difficult for fake profiles to impersonate real
individuals.
7. Real-time Chat Analysis:
 Implement real-time analysis of chat conversations to identify suspicious
language, phishing attempts, or other scam-related content in private
messages.
8. Community Voting System:
 Allow the community to vote on the authenticity of profiles or reported
content. Collective voting can help in the decision-making process regarding
suspicious accounts.
9. Deep fake Detection:
 Integrate deep fake detection algorithms to identify manipulated images or
videos, which are commonly used in fake profiles.
10. Scam Pattern Recognition:
 Develop algorithms that recognize common scam patterns and techniques
used by fake profiles, improving the system's ability to detect new, evolving
scams.
11. User Feedback Loop:
 Establish a feedback loop where users can provide feedback on the
effectiveness of the platform's fake profile detection mechanisms, allowing
continuous improvements.
12. Collaboration with Cybersecurity Experts:
 Collaborate with cybersecurity experts and researchers to stay updated on the
latest fraud tactics and implement cutting-edge detection methods.

5. Non-Functional Requirements

4.1 Performance

 Requirement 4.1.1: The system must handle a minimum of 1000 concurrent users
without significant performance degradation.
 Requirement 4.1.2: Fake profile detection should take no longer than 10 seconds
per profile.

4.2 Security
 Requirement 4.2.1: User passwords must be securely hashed and stored.
 Requirement 4.2.2: Communication between the client and the server must be
encrypted using HTTPS.

4.3 Usability

 Requirement 4.3.1: The user interface must be intuitive and easy to navigate,
ensuring a seamless experience for users.

4.4 Maintainability

Maintainability is a critical non-functional requirement for any software system, including

fake profile detection and reporting platforms. It refers to the ease with which the system
can be modified, enhanced, or repaired over its operational lifespan. In the context of fake
profile detection and reporting systems, maintainability ensures that the platform can adapt
to changing threats, technology advancements, and user requirements without
compromising its efficiency, accuracy, and security.

6. Other Requirements:

In the context of developing a fake profile detection and reporting system, the
"Other Requirements" section encompasses specific criteria, constraints, and
conditions that are integral to the success of the project. These requirements go
beyond the core functionalities and technical aspects of the system, focusing on
various essential elements.

1. Legal and Compliance Requirements:

 The system must adhere to all applicable data protection laws and regulations,
ensuring the privacy and security of user data.
 Compliance with local and international cybercrime laws is mandatory, as the
system deals with identifying and reporting fraudulent activities.
2. Training and Support:
 Comprehensive user training materials, including tutorials and guides, should
be provided to educate users on how to recognize fake profiles and report
them effectively.
 A dedicated support system, such as email support or a helpline, must be
established to assist users facing challenges in reporting suspicious accounts.
3. Performance Metrics:
 The system should aim for high accuracy in identifying fake profiles, measured
through metrics such as precision, recall, and F1 score.
 Response time for processing user reports should be minimized to enhance
user experience and encourage active participation in reporting suspicious
activities.
4. Constraints:
  The system should be compatible with various platforms and devices,
ensuring users can access the reporting functionality seamlessly from
desktops, smartphones, and tablets.
 Integration with social media platforms' APIs and adherence to their usage
policies and rate limits are critical constraints to consider.
5. User Experience (UX) Requirements:
 The user interface should be intuitive and user-friendly, guiding users through
the process of reporting fake profiles step by step.
 Accessibility features, such as alt text for images and keyboard navigation,
should be implemented to accommodate users with disabilities.
6. Security Requirements:
 Robust encryption protocols must be implemented to secure user data during
transmission and storage.
 Multi-factor authentication should be enforced for users accessing the
reporting system to prevent unauthorized access.
7. Maintenance and Support:
 Regular maintenance schedules, including software updates and security
patches, are essential to keep the system resilient against evolving threats.
 User support services should be available round-the-clock to address user
queries and issues promptly, ensuring a positive user experience.

Appendix A: Glossary:

Common Terms and Acronyms:

 Fake Profile: A deceptive online account created with false information to

impersonate a real person or entity.
 Reporting System: The platform or mechanism allowing users to flag suspicious
profiles for review.
 API: Application Programming Interface, enabling interaction between different
software applications.
 F1 Score: A metric combining precision and recall, used to evaluate the accuracy of
the fake profile detection algorithm.

Appendix S: Analysis Models:

User Flow Diagram:

A visual representation outlining the steps users take to identify and report a fake
profile within the system. This diagram illustrates the user journey, from recognizing
suspicious activity to submitting a detailed report, guiding developers and
stakeholders on the system's user interactions.

Data Flow Diagram:

A graphical representation demonstrating the flow of data within the fake profile
detection and reporting system. This model illustrates how user reports are
processed, verified, and, if necessary, escalated for further action. It provides a clear
overview of the system's data handling processes.

These appendices and additional requirements ensure that the fake profile detection
and reporting system is not only technically robust but also user-friendly, legally
compliant, and secure, meeting the needs of both users and regulatory standards.

7. Conclusion

The Fake Social Media Profile Detection and Reporting System outlined in this
document will provide users with a reliable tool to identify and report fake profiles
on social media platforms. By implementing advanced algorithms and user-friendly
interfaces, the system aims to enhance online safety and trust in social media
interactions.

(22070393)