ALPR / ANPR Tracking Risk

#!/bin/bash
# Prerequisites: pip install shodan censys
# Requires: Shodan API key (export SHODAN_API_KEY=...) and Censys API credentials
# Discover publicly documented ALPR deployments (legal OSINT only)

# EFF Atlas of Surveillance — search for ALPR deployments
echo "Search: https://atlasofsurveillance.org/search?tech=alpr"

# Check local government transparency portals for ALPR policies
# Many agencies publish ALPR retention policies and audit reports

# Shodan: discover exposed ALPR-related infrastructure (authorized only)
shodan search "ALPR" --fields ip_str,port,org,country_code --limit 25
shodan search "plate recognition" --fields ip_str,port,org --limit 25

# OpenALPR cloud instance discovery (for security researchers)
shodan search 'http.title:"OpenALPR"' --limit 10

#!/usr/bin/env python3
# Prerequisites: pip install easyocr opencv-python numpy
"""Test license plate OCR accuracy under various conditions.
Use this to understand ALPR system capabilities and limitations."""
import cv2
import numpy as np

# Option 1: OpenALPR (open source)
# pip install openalpr
# from openalpr import Alpr
# alpr = Alpr("us", "/etc/openalpr/openalpr.conf", "/usr/share/openalpr/runtime_data")

# Option 2: EasyOCR (no commercial dependencies)
import easyocr
reader = easyocr.Reader(['en'])

# ⚠ Create plates/ directory with test images: various angles (0°, 15°, 30°, 45°), distances (5m, 10m, 20m), and lighting conditions
conditions = {
    "clean_daylight": "plates/clean_day.jpg",
    "distance_30m": "plates/distance_30m.jpg",
    "angle_45deg": "plates/angle_45.jpg",
    "low_light": "plates/low_light.jpg",
    "rain_glare": "plates/rain_glare.jpg",
    "partial_occlusion": "plates/partial_occluded.jpg",
    "dirty_plate": "plates/dirty.jpg",
    "motion_blur": "plates/motion_blur.jpg",
}

print(f"{'Condition':<25} {'OCR Result':<20} {'Confidence':>10}")
print("-" * 58)
for condition, path in conditions.items():
    img = cv2.imread(path)
    if img is None:
        print(f"{condition:<25} {'FILE NOT FOUND':<20}")
        continue
    
    # Preprocess (grayscale + contrast enhancement)
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    enhanced = cv2.equalizeHist(gray)  # Histogram equalization normalizes contrast — simulates how ALPR pre-processes images for consistent OCR
    
    results = reader.readtext(enhanced)
    if results:
        text = results[0][1]
        conf = results[0][2]
        print(f"{condition:<25} {text:<20} {conf:>10.3f}")
    else:
        print(f"{condition:<25} {'NO DETECTION':<20} {'0.000':>10}")

# --- Expected Output ---
# Condition                 OCR Result           Confidence
# ----------------------------------------------------------
# clean_daylight            ABC 1234                  0.987
# distance_30m              ABC 1Z34                  0.724
# angle_45deg               A8C 1234                  0.681
# low_light                 A8C I234                  0.512
# rain_glare                NO DETECTION              0.000
# partial_occlusion         AB  123                   0.443
# dirty_plate               A C  2 4                  0.298
# motion_blur               NO DETECTION              0.000

#!/bin/bash
# Informational checklist — not an automated scan. Use as a reference guide for manual telematics review.
# Audit vehicle telematics data exposure

echo "=== Connected Vehicle Data Sources to Review ==="
echo "1. Manufacturer app (Ford Pass, MyChevrolet, Toyota Connected, etc.)"
echo "   → Check: Location history, trip logs, driving behavior data"
echo "   → Action: Disable data sharing, delete history, opt out of marketing"
echo ""
echo "2. Insurance telematics (Progressive Snapshot, State Farm Drive Safe)"
echo "   → Check: Location data collection, driving pattern scoring"
echo "   → Action: Understand what data is collected & how long retained"
echo ""
echo "3. Toll transponders (E-ZPass, SunPass, FasTrak)"
echo "   → Check: Transaction logs reveal exact route and timing"
echo "   → Action: Review statement history, understand retention period"
echo ""
echo "4. OBD-II aftermarket devices (Automatic, Hum, fleet trackers)"
echo "   → Check: Hidden GPS trackers plugged into diagnostic port"
echo "   → Action: Physically inspect OBD-II port"
echo ""
echo "5. Rental/fleet vehicles"
echo "   → Check: GPS tracking typically active, may have cameras"
echo "   → Action: Understand rental agreement data clauses"

echo ""
echo "=== Physical OBD-II Port Inspection ==="
echo "Location: Usually under dashboard, driver side, near steering column"
echo "Check for: Unknown devices plugged into the 16-pin port"
echo "Note: Hidden GPS trackers can also be magnetic, check wheel wells"