Mass Registration 2018-06-13T15:30:31+00:00

Mass Registration

Mass registration is the foundation of most sophisticated online attacks. Facebook and Twitter recently disclosed as many as 270M and 48M accounts on their respective platforms are fake. Fraudsters start by mass registering an army of accounts and then camouflaging them with real-looking user activity. When these accounts are later used for an attack, they are much harder to detect with existing solutions. DataVisor’s Unsupervised Machine Learning Engine is uniquely capable of detecting these mass-registered accounts because it uncovers the hidden connections between accounts, even if those accounts have not yet done any damage or started their attack. This allows companies to quarantine or add extra authentication steps to suspicious accounts and stop them before they strike.

How Attackers Mass Register Accounts 

Fake user activity for mass registration

Fake User Activity

Attackers simulate user activity by uploading stolen photos and content from other sites, making them appear real even to human reviewers.

device obfuscation for mass registration

Device Obfuscation

Fraudsters utilize mobile device flashing, virtual machines and scripts to appear as though the login events are coming from different devices.
Stolen identities for mass registration

Stolen Identities

Attackers use readily-available stolen credentials or information from data breaches to create authentic-looking new accounts.

location spoofing for mass registration

IP Obfuscation

Proxies, VPNs, and cloud-hosting services allow attackers to evade IP or location blacklists and digital-fingerprint solutions.

How Unsupervised Machine Learning Stops Mass Registration

There are many challenges when it comes to mass registration detection. For one, the amount of data is limited at registration. Further, falsely rejecting a real customer at account opening can prevent a legitimate person from signing up with the service. DataVisor’s Unsupervised Machine Learning Engine looks at a new registration in the context of millions of recent registrations, deriving and analyzing a rich array of features, in order to determine if there are any suspicious similarities between the newly registered accounts. This allows the UML Engine to adapt in real-time as fraudsters change their attack techniques, keeping your online service free of fake accounts and the downstream havoc they attempt to conduct.

Detect Mass Registration with Accuracy and Coverage

Early Detection

Detect malicious intent at point of registration, preventing downstream damage

high accuracy and coverage to detect account takeover

Accuracy and Coverage

Analyze hidden connections between accounts to detect more attacks while lowering false positives.

Detect unknown mass registration

Unknown Threat Detection

Uncover new and evolving attack patterns without any training data or labels.

Learn More About How DataVisor Stops Mass Registration

The DataVisor Platform

Unsupervised Machine Learning Engine

Predict new, unknown threats without labels or training data by analyzing hundreds of millions of accounts and events simultaneously using the industry’s most advanced unsupervised learning technology.

Supervised Machine Learning Engine

Use industry leading supervised machine learning algorithms to augment the unsupervised machine learning detection with client-provided labels.

Automated Rules Engine

Generate and deprecate rules automatically, lowering maintenance costs and improving results explainability.

Global Intelligence Network

Aggregate and analyze the industry’s broadest array of digital fingerprints and signals from billions of users across a variety of industries.

Learn More

What’s Happening with Mass Registration

Read the Blog

Ready to enhance your detection with unsupervised machine learning?

Request Trial