JP-Morgan-and-Chase-Internship-in-Cybersecurity.pdf

it is the ppt about my internship at the jpmc where i learn about the fraud detection model for the banking data of jpmc

1. JP Morgan & Chase
- Internship in
Cybersecurity
This presentation outlines my internship experience at JP Morgan
& Chase in Cybersecurity.
by Abhay

2. Company Overview
1
1799
Founded as a bank in New York City.
2
1990s
Expansion into investment banking and asset
management.
3
2000s
Focus on cybersecurity and technology innovation.

3. Cybersecurity in Financial Institutions
Vital Importance
Protect sensitive financial data and customer
information.
Growing Threats
Cybercrime cost $1.5 trillion in 2023.

4. Fraud Detection in Financial Services
Data Analysis
Using Pandas and Matplotlib for
fraud detection.
Machine Learning
Developing models to identify
fraudulent patterns.
Real-Time Monitoring
Implementing systems to detect
and prevent fraud in real-time.

5. Web Application Security
Vulnerability Assessment
Identifying potential security weaknesses.
Mitigation Strategies
Implementing solutions to address vulnerabilities.
Continuous Monitoring
Regularly scanning for new threats and vulnerabilities.

6. Email Classifier Using
Machine Learning
1
Spam Detection
Classifying emails as spam or legitimate.
2
Phishing Prevention
Identifying and blocking phishing emails.
3
Data Analysis
Analyzing email data to improve classification accuracy.

7. Access Control System
Design
Role Permissions
Administrator Full access to all systems
and data.
User Limited access to specific
systems and data.

8. Tools Learned
Python
Programming language for data analysis and machine learning.
Pandas
Data manipulation and analysis library.
Django
Web framework for building secure web applications.
Scikit-learn
Machine learning library for building classification models.

9. Research & Gap Analysis
1
False Positives
Identifying and reducing false positives in fraud detection.
2
Security Gaps
Analyzing system vulnerabilities and identifying areas for
improvement.
3
Data Accuracy
Ensuring data quality and accuracy for effective analysis.

10. Objectives
1
Fraud Detection
Improve fraud detection accuracy and efficiency.
2
Web Security
Implement secure coding practices and mitigate
vulnerabilities.
3
Access Control
Enhance access control mechanisms to protect sensitive
data.

11. JP Morgan & Chase
Overview
JP Morgan's global leadership in financial services and
cybersecurity innovations.
cc
by caleb curry

12. Cybersecurity in
Financial Services
1
Threats
Phishing, fraud, and ransomware targeting financial
institutions.
2
Statistics
Cybercrime cost $1.5 trillion in 2023.
3
Importance
Securing global financial systems is critical.

13. Task 1: Fraud Detection in Financial
Services
Fraud Detection
Analyzing financial transaction data
to detect fraudulent activity.
Tools Used
Pandas, Matplotlib for data analysis
and visualization.
Approach
Machine learning techniques to
identify suspicious transactions.

14. Task 2: Web Application
Security (Django)
Vulnerabilities
Addressed OWASP issues like XSS, SQL Injection.
Secure Coding
Implemented input validation, session management,
authentication.
Secure Application
Designed a secure Django web application.

15. Task 3: Spam vs Ham - Email Classifier
Machine Learning
Utilized Naive Bayes, Logistic
Regression algorithms.
Performance
Evaluated precision and recall of
the classifier.
Workflow
Preprocessing, training, and testing
the model.

16. Task 4: Access Control & Role Management
Access Control
Designed a system to manage
user roles and permissions.
Least Privilege
Restricted access based on the
principle of least privilege.
Security Model
Layered approach with user roles,
permissions, and access control.

17. Tools & Technologies Used
Pandas
Data manipulation and analysis.
Django
Web application development
framework.
Scikit-learn
Machine learning algorithms and
models.
Matplotlib
Data visualization and charting.

18. Cybersecurity Techniques
Fraud Detection
Analyzed financial data to
identify fraudulent
transactions.
Secure Coding
Implemented secure coding
practices in Django
application.
Email Classification
Utilized machine learning to
classify emails as spam or
legitimate.
Access Control
Designed a role-based
access control system.

19. Research & Gap Analysis
Fraud Detection Gaps
Identified areas to improve fraud detection accuracy and reduce false positives.

20. Problem Formulation
Problems
Fraud detection accuracy, web application security, and
access control.
Solutions
Proposed solutions to address the identified challenges.

21. Project Objectives
Enhance fraud detection, apply secure coding, classify emails,
and enforce access control.
cc
by caleb curry

22. Methodology
1
Fraud Detection
Data cleaning to model training using Pandas.
2
Web Security
Applying security measures with Django and
OWASP.
3
Email & Access Control
ML classification workflow and access control
design.

23. System Design
Fraud Detection
Data pipeline diagram showing the entire process.
Web Security
Architecture diagram with secure coding and
database.

24. Performance Comparison
Fraud Detection
Table comparing precision, recall, and accuracy.
Web Security
Bar chart comparing vulnerabilities before and after.
ML Models
Line graph comparing Naive Bayes and Logistic Regression.