Cybersecurity
Network Intrusion Detection System
Machine-learning anomaly detection over live network traffic
- Python
- Scapy
- XGBoost
- Kafka
- +2
Cybersecurity · Major Project
Flags risky APKs from their requested permissions and API calls
Overview
Static analysis extracts the permissions and sensitive API calls declared in an APK's manifest and bytecode, then a classifier trained on a public benign-versus-malware dataset scores how risky the app looks. Nothing is installed or run; the APK is only parsed. A web tool accepts an APK and returns the verdict with the permissions that raised the flag.
What makes it stand up
Module breakdown
Parses the manifest and bytecode with Androguard for features.
Loads labelled benign and malicious apps and builds vectors.
Trains a classifier and reports precision, recall and F1.
Ranks the permissions and calls driving each verdict.
Accepts an APK upload and shows its risk breakdown.
After this, you will be able to
Technology stack
You receive
Keep looking
Cybersecurity
Machine-learning anomaly detection over live network traffic