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
Image Forgery Detection
Flags spliced and copy-move edits using error level analysis and a CNN
3-4 weeks build
Overview
A digital forensics tool for checking whether a photo has been tampered with. Error level analysis exposes regions recompressed differently from the rest, a CNN trained on the public CASIA v2 dataset classifies the image as authentic or tampered, and a keypoint-matching module localises copy-move regions. Results are presented as an examiner-style report.
What makes it stand up
- 01Error level analysis maps as CNN input
- 02Authentic versus tampered classifier trained on CASIA v2
- 03SIFT keypoint matching to localise copy-move regions
- 04EXIF metadata inspection for editing-software traces
- 05Downloadable forensic report per analysed image
Module breakdown
- 01
ELA
JPEG recompression and difference amplification.
- 02
Classifier
CNN trained on ELA maps of authentic and tampered images.
- 03
Copy-move detection
Keypoint clustering to highlight duplicated regions.
- 04
Metadata
EXIF parsing for software tags and timestamp mismatches.
- 05
Report
Flask page that exports findings as a PDF.
After this, you will be able to
- Explain why recompression reveals edited regions
- Discuss the limits of forensics on heavily compressed images
- Demo detection on an image edited live during the viva
Technology stack
- Python
- TensorFlow
- OpenCV
- Flask
- scikit-learn
- Level
- Major Project
- Domain
- Cybersecurity
- Build time
- 3-4 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