← Challenge Hub
Cybersecuritydata-analyst

Network Intrusion Detection

Build a classifier to detect anomalous network traffic patterns in African ISP data.

Learn First

  1. 1

    Introduction & Ethics

    Introduction

    Understand the data sources, formats, and the ethics of working with African data.

    • Where the data comes from
    • What questions it can answer
    • Responsible use
  2. 2

    Data Cleaning Fundamentals

    Data Cleaning

    Handle missing values, outliers, and inconsistencies.

    import pandas as pd
df = pd.read_csv("data.csv")
df = df.dropna()
  3. 3

    Exploratory Data Analysis

    Exploratory Data Analysis

    Visualize patterns across regions and time.

    • Distributions
    • Correlations
    • Trends by district
  4. 4

    Modeling & Evaluation

    Modeling

    Build and evaluate a simple model, then write your recommendations.

    • Train/test split
    • Baseline model
    • Metrics that matter

Dataset

Title
ISP Network Flow Samples
Country
Multi-country
Source
Research partner (anonymized)
License
CC BY-NC 4.0
Ethics note
Anonymized traffic. Research/education use only.
Open dataset →Data dictionaryDataset details

Instructions

Goal

Classify network flows as benign or anomalous.

The data

Use the linked NSL-KDD network-flow dataset.

Steps

  1. Open the starter notebook in Colab.
  2. Encode categorical features and scale the inputs.
  3. Train a classifier and tune the decision threshold.
  4. Report precision/recall — false negatives are costly here.

Deliverables

  • Your Colab notebook link
  • A confusion matrix + short write-up

How to submit

Sign in and paste your work links in Submit your work for mentor review.

Rubric

  • Data Cleaning20 pts
  • Exploratory Analysis20 pts
  • Visualizations20 pts
  • Model / Evaluation20 pts
  • Report / Recommendations20 pts
  • Total100 pts