AI Use Case

Detect fake biometric credentials

The rise of biometric-based security systems poses risks that fake credentials - photographs, scans, copies or even post-mortem presentation - may be offered to fool security systems. Image recognition is used to scan for and observe minute differences that may suggest the credentials are invalid.

Function

Risk

Security

Benefits

Risk reduction - Reduce data theft risk,Risk reduction - Spot issue (eg copyright infringement)

Case Studies

Warsaw University of Technology~Researchers from Warsaw University of Technology identify irises as live or dead with a mean accuracy of 98.94% using convolutional neural networks,New York University ~Researchers generate fake fingerprints using neural networks and successfully trick fingerprint matching security systems

Industry

Public And Social Sector

Security

Data Sets

Images,Audio

AI Technologies

ML Task - Prediction - Binary Classification,ML Task - Prediction - Multi-class Classification,ML Task - Grouping - Anomaly Detection,Machine Learning (ML)

Potential Vendors