# I Taught a Computer to Spot Fake Websites With 96% Accuracy

> Source: <https://dev.to/eln2mac/i-taught-a-computer-to-spot-fake-websites-with-96-accuracy-3ikh>
> Published: 2026-09-29 20:15:53+00:00

What if a computer could tell a fake website is fake just by looking at its URL — without ever opening it? Turns out, yes. Here's how I built my first real machine learning project.

If you've ever gotten a message saying "Your bank account is suspended, click here now," you've seen phishing in action — fake websites disguised as real ones, built to steal your password or credit card number.

Traditional defenses (blacklists of known bad URLs) are always playing catch-up. Attackers spin up new fake domains faster than blacklists can be updated.

Instead of memorizing bad URLs, what if a model learned the shared traits of phishing sites? Things like:

I used the UCI Phishing Websites dataset — 11,055 real websites, each labeled phishing or legitimate, described by 30 features.

I trained and compared three classic ML algorithms:

| Algorithm | Accuracy | 
|---|---|
| Logistic Regression | 92.45% | 
| Random Forest | 96.70% 🏆 | 
| SVM | 94.71% | 

When I checked which features mattered most, SSL certificate state and anchor link behavior dominated — by a wide margin over the other 28 features.

Why? Because phishing sites usually:

The model figured this out on its own — I never told it to focus on SSL.

The biggest lesson: you don't need to be an expert to start. The dataset was ready-made, the tools (Python + scikit-learn) are free, and the steps are well-documented. What it actually took was patience and consistency.

Full code and details are on GitHub:

🔗 [https://github.com/eln2mac-has/phishing-detection-ml](https://github.com/eln2mac-has/phishing-detection-ml)

If you try something similar or have questions, drop a comment below 👇