Inference & Profiling · Company practice
Device Intelligence scores fraud risk from device and behaviour signals
Device Intelligence – Standard analyses technical data, device signals, IP address, geolocation and other fraud signals, collected via the SDK or standard tracking technologies such as JavaScript snippets as Users interact with the services, to assess the likelihood that the User is genuine. The listed categories include device fingerprints and identifiers (audio and video fingerprints, Android/Google Advertising ID, hardware identifiers such as MAC address); uploaded images and videos with metadata; device and browser attributes such as type, model, operating system, browser, screen details, plugins, fonts and battery information; behaviour data such as start/stop times, fields completed, pointer and touch events and distraction events; application authenticity (whether the device uses stolen security tokens); IP address type, location and detection of masking tools such as a VPN or Proxy; and risk scores or levels inferred from those signals. Other fraud signals are listed in the API Documentation.
Details
- What it does
- analyses device, location and behaviour signals
- Why
- assess the likelihood the User is genuine
- What it covers
- risk scores, device identifiers, IP and geolocation, behaviour and fraud signals
Supporting quotations
| Categories of Personal Data: ● Onfido User unique identifier ● Document number and other data extracted from any associated document check; ● IP address and IP address type, including associated city/region/country level location and detection of any IP masking tools such as a VPN or Proxy; ● Check status/outcome and related tracking information; ● Inferences and outputs from Device Intelligence e.g. risk score, risk level;
Analysis of technical data, device signals, IP address, geolocation, and other fraud signals (collected via the SDK or standard tracking technologies (e.g. JavaScript snippets) from Users as they interact with the Onfido Identity Services) to assess the likelihood that the User is genuine
● Device Fingerprint, device identifiers including audio and video fingerprint, Android/Google Advertising ID (AAID or GAID), hardware-based identifiers (e.g. MAC address)
● Images and videos uploaded by U ser and any related metadata and metatags
● Information about Users' device including hardware and software attributes (e.g. device type and model, manufacturer, operating system type and version (e.g. iOS or Android), browser type and version, user-agent, navigator, screen details, plugins, fonts, memory, WebGL, battery information, language, time zone, camera name, microphone name, aspect ratio, resolution, frame rate, etc.)
● Information about a User’s behaviour when interacting with the Onfido Identity Services, including how the User uses the Onfido Identity Services such as start/stop time, forms/fields completed, pointer and touch events, time zone offset, distraction events
● Application Authenticity - Whether the device is using stolen security tokens
Qualifications & exceptions
- Collection can occur through the SDK or standard tracking technologies such as JavaScript snippets.
- Risk scores and levels are described as inferences and outputs of the service.
Not stated here
- The API Documentation's further fraud signals are not supplied, and the notice does not state retention for these signals.