Capstone
Cybersecurity
Network Intrusion Detection System
Machine-learning anomaly detection over live network traffic
- Python
- Scapy
- XGBoost
- Kafka
- +2
₹5,499₹9,499
4.9/97 reviews
Cybersecurity · Major Project
SQL Injection Detection
Classifies query payloads and blocks malicious ones in web middleware
2-3 weeks build
Overview
Learns to tell injection payloads from ordinary input using a public labelled dataset, character n-grams and token features such as quotes, comments and boolean tautologies. The trained model sits in Flask middleware in front of a deliberately simple demo app, logging and rejecting suspicious parameters before they reach the query layer.
What makes it stand up
- 01Character n-gram and hand-built token features compared side by side
- 02Logistic regression, SVM and random forest on the same split
- 03Request middleware that flags and rejects suspicious parameters
- 04Demo shop app shown both unprotected and protected
- 05Report explains why parameterised queries remain the real fix
Module breakdown
- 01
Dataset
Cleans labelled payloads and balances the benign and malicious classes.
- 02
Features
Builds n-gram vectors plus counts of keywords and symbols.
- 03
Classifier
Trains and compares three models with per-class F1 scores.
- 04
Middleware
Scores each query parameter and rejects those above a threshold.
- 05
Alert log
Dashboard of blocked requests with the payload that triggered them.
After this, you will be able to
- Explain the query-manipulation patterns the model learns to flag
- Defend where a classifier helps and where prepared statements suffice
- Demo a flagged payload being rejected by the middleware
Technology stack
- Python
- scikit-learn
- Flask
- PostgreSQL
- Pandas
- Level
- Major Project
- Domain
- Cybersecurity
- Build time
- 2-3 weeks
- Difficulty
You receive
- Complete, commented source code
- 60-90 page project report (IEEE format)
- Editable presentation deck
- Architecture, ER and UML diagrams
- Local setup and deployment guide
- Sample dataset or seed data
- Viva question bank with answers
- One 45-minute walkthrough call
- 30 days of doubt-clearing support