Simon commited on
Commit
1e3001a
·
1 Parent(s): a808589

Add initial site configuration and content for phishing detection model (#12)

Browse files
gitpage/.gitignore ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ _site/
2
+ .sass-cache/
3
+ .jekyll-cache/
4
+ .jekyll-metadata
5
+ Gemfile.lock
gitpage/_config.yml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ title: Phishing Detection Model
2
+ description: Machine learning model performance and metrics for phishing URL detection
3
+ theme: jekyll-theme-minimal
4
+ show_downloads: false
5
+
6
+ # GitHub repository info (update if needed)
7
+ github:
8
+ repository_url: https://github.com/yourusername/ID2223-project
9
+ is_project_page: true
gitpage/images/confusion_matrix.png ADDED
gitpage/images/feature_drift.png ADDED
gitpage/images/performance_over_time.png ADDED
gitpage/index.md ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ layout: default
3
+ ---
4
+
5
+ # Phishing Detection Model Performance
6
+
7
+ ## Overview
8
+
9
+ This project develops a machine learning model for detecting phishing URLs using URLScan.io API data.
10
+
11
+ ## Model Performance Over Time
12
+
13
+ ### Performance Metrics
14
+
15
+ Track how the model's performance evolves over time to identify improvements or degradation.
16
+
17
+ ![Performance Over Time](images/performance_over_time.png)
18
+
19
+ ### Confusion Matrix
20
+
21
+ Latest model confusion matrix showing prediction accuracy across classes.
22
+
23
+ ![Confusion Matrix](images/confusion_matrix.png)
24
+
25
+ ### Feature Drift Detection
26
+
27
+ Monitor feature drift to detect changes in data distribution that may affect model performance.
28
+
29
+ ![Feature Drift](images/feature_drift.png)
30
+
31
+ ## Dataset Information
32
+
33
+ - **Source**: URLScan.io API + Phishing URL datasets
34
+ - **Training samples**: TBD
35
+ - **Test samples**: TBD
36
+ - **Features**: TBD
37
+
38
+ ## Model Architecture
39
+
40
+ Details about the model architecture, feature engineering, and training process will be documented here.
41
+
42
+ ## Latest Updates
43
+
44
+ Check back for updates on model performance and improvements.
45
+
46
+ ---
47
+
48
+ _Last updated: {{ site.time | date: "%Y-%m-%d" }}_