Added PDF malware detection feature to app

[DarshAgrawal14]

hey @yashasvini121

Description

• created model on pdf malware detection
• created program to extract features from given pdf
• created page to accept and upload pdfs and show result
• integrated model with page
• successfully integrated page with app

Issue Resolved

Fixed Issue : #93

Changes Made

Screenshots or Videos

https://github.com/user-attachments/assets/cf6ff784-4155-4acc-8a7a-477e99882ba3

Additional Details

Checklist

• [x] My code follows the current project structure
• [x] I have thoroughly reviewed and updated the requirements.txt file to include any new packages
• [x] The predict.py file includes a properly implemented model_details() function, or the notebook contains this function to print a detailed model report. The model will not be accepted without this function, as it is essential for generating the necessary model details.
• [x] I have added relevant tests (if necessary).
• [x] I have added comments in the code where needed.
• [x] This PR is submitted under Hacktoberfest.
• [x] This PR is submitted under GirlScript Summer of Code (GSSoC-Extd).

[DarshAgrawal14]

@yashasvini121 , please let me know if any further changes are needed. Otherwise, I would appreciate it if you could merge the PR.

[yashasvini121]

I’ve accepted the PR, but it still has this issue. Please see if you can resolve it without downgrading the package versions.

[DarshAgrawal14]

did you re pip install the requirements.txt? because extraction requires certain modules

[yashasvini121]

Yup I added them

[DarshAgrawal14]

@yashasvini121 i have retrained the model , so how to want me to proceed , create a new issue ?

[yashasvini121]

yup

[DarshAgrawal14]

and the issue was mostly because the scikit-learn version were not matching , the model is trained on version 1.3.2 and the one mentioned in requirements is 1.5.2

[DarshAgrawal14]

@yashasvini121 ,The assigned level is 2; however, I believe extracting features from PDFs and developing a page to accept PDF along with model creation aligns more appropriately with a level 3 classification. I would appreciate your consideration of this adjustment.

[yashasvini121]

• The reported accuracy is exceptionally high, suggesting a high likelihood of overfitting
• A dedicated function to retrieve and display model details is absent.
• The model details tab is missing and needs to include key metrics and relevant information, visualizations, such as performance plots and feature importance etc.
• The Jupyter notebook lacks thorough data analysis, proper exploratory data exploration (EDA), and experimentation with multiple models to ensure robust performance.
• The project structure is not organized correctly; eg: the notebook should be placed in a dedicated folder or separated from core project files.

Based on these, the pr has been assigned Level 2.