Sting9 Logo

Building the World's Most ComprehensiveAnti-Phishing Dataset

An open-source research initiative collecting phishing, smishing, and scam messages to train AI models capable of detecting malicious communications with 99.9% accuracy.

5.3B phishing emails sent daily
$10.3B lost to scams annually
1 in 3 people have fallen victim

Quick submission via email forwarding

Simply forward suspicious emails to submit@sting9.org and we'll automatically process them.

All submissions are automatically anonymized. No tracking. GDPR compliant.

Live Dataset Statistics

Real-time progress toward our goal of 1 million messages

5,547
Messages Collected
12+
Languages Supported
8
Countries Contributing
45+
Attack Types Identified
Progress to 1M Goal0.55%

Every submission brings us closer to 99.9% detection accuracy

Top Contributors

Recognizing the heroes who help build the world's largest phishing detection dataset

Loading leaderboard...

How It Works

From submission to protection in four transparent steps

1

Submit Suspicious Message

Forward phishing emails or paste smishing texts. Upload screenshots or message files. Anonymous submissions welcome.

2

Automated Anonymization

Our system immediately redacts all personal information—emails, phone numbers, names, addresses, and identifiers—to protect your privacy.

3

Added to Open Dataset

The anonymized message joins our CC0 public dataset, categorized by type, language, and threat characteristics for research access.

4

Powers AI Detection

Your contribution trains machine learning models used by individuals, organizations, and researchers to detect and prevent future attacks.

Your Contribution Matters

Every message you submit helps protect millions of people from digital deception. Together, we're building the most comprehensive anti-phishing defense system ever created.

Learn more about our mission

The Impact We're Creating

From open data to global protection, our mission reaches millions

What This Dataset Enables

99.9%

99.9% Accurate AI Models

State-of-the-art machine learning trained on the largest, most diverse phishing dataset ever created.

Real-time

Real-Time Threat Intelligence

Live feeds of emerging attack patterns, malicious URLs, and new scam techniques as they appear.

Free

Open Research Access

Free API and dataset downloads for academic researchers, developers, and security professionals worldwide.

Who Benefits

Individuals

Everyday users gain protection through email clients, messaging apps, and browsers powered by our detection models.

Organizations

Businesses integrate our API to protect employees from BEC, credential harvesting, and targeted phishing campaigns.

Researchers

Academic institutions and security labs use our dataset to advance cybersecurity science and develop new defenses.

Our Open-Source Commitment

ODC-BY-NC License
Open Data Commons Attribution-NonCommercial—free for research and non-commercial use
Free API Access
RESTful API for researchers and developers—no paywalls
Transparent Methodology
Open documentation of collection, anonymization, and classification processes
Pre-Trained Models
Detection models freely available for personal and research use

"Making digital deception obsolete through radical transparency and collaboration"

Educational Examples

Learn to Spot the Red Flags

Real examples from our dataset (anonymized and redacted) showing common phishing and smishing techniques

Fake Package Delivery

BEC / Impersonation
From: delivery@amaz0n-support.com Subject: Your package is waiting - Action Required! Dear Customer, Your package has been held due to incomplete address information. Click here to update your delivery details within 24 hours or your package will be returned...

Red Flags to Watch For

  • 1
    Suspicious sender domain (amaz0n with zero)
  • 2
    Urgency tactics ("within 24 hours")
  • 3
    Generic greeting ("Dear Customer")
  • 4
    Unsolicited link to update information

Bank Account Alert

Credential Harvesting
ALERT: Unusual activity detected on your account ending in 3847. Verify your identity immediately: http://bit.ly/2xK9pL If you did not authorize this transaction, click the link now to prevent further charges. -Your Bank Security Team

Red Flags to Watch For

  • 1
    Shortened URL hiding real destination
  • 2
    Creates panic with "unusual activity"
  • 3
    No official branding or identifiers
  • 4
    Pressure to act immediately

Prize Winnings Notification

Advance Fee Fraud
From: winners@international-lottery-commission.biz Subject: CONGRATULATIONS! You've Won $2,500,000 USD Dear Lucky Winner, You have been selected as the winner of our international sweepstakes. To claim your prize, please provide your bank details and pay a processing fee of $450...

Red Flags to Watch For

  • 1
    Unsolicited prize notification
  • 2
    Request for payment to receive winnings
  • 3
    Asks for sensitive bank information
  • 4
    Too good to be true offer

Help Us Educate Others

When you submit a suspicious message, you're not just protecting yourself—you're helping us identify new attack patterns and educate millions of people worldwide about emerging threats.