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
Cyberbullying Detection
Classifies abusive messages and queues them for human moderation
2-3 weeks build
Overview
Scores messages for abuse type, such as insults, threats and identity-based harassment, using the public Jigsaw toxic comment data from Kaggle. A TF-IDF baseline is compared with a fine-tuned transformer, and flagged messages land in a moderation dashboard where a human confirms or overturns each call, feeding corrections back as training data.
What makes it stand up
- 01Multi-label abuse classification across several categories
- 02Classical baseline and transformer compared in the report
- 03Text normalisation for slang, repeated letters and masked words
- 04Moderation queue with confirm, overturn and notes
- 05Per-label precision, recall and threshold analysis
Module breakdown
- 01
Preprocessing
Cleaning, normalisation and label balancing.
- 02
Models
TF-IDF logistic regression and a fine-tuned DistilBERT.
- 03
Scoring API
FastAPI endpoint returning per-label probabilities.
- 04
Moderation dashboard
React queue with actions and an audit trail.
- 05
Evaluation
Per-label metrics and a bias check on identity terms.
After this, you will be able to
- Explain multi-label classification and threshold tuning
- Defend keeping a human in the moderation loop
- Demo messages being scored and moderated live
Technology stack
- Python
- scikit-learn
- PyTorch
- FastAPI
- React
- 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