Let It Snow: Adding pixel noise to protect the user’s identity
Brendan John, Ao Liu, Lirong Xia, Sanjeev J. Koppal, Eakta Jain
Abstract
Optical eye trackers record images of the eye to estimate the gaze direction. These images contain the iris of the user. While useful for authentication, these images can be used for a spoofing attack if stolen. We propose to use pixel noise to break the iris signature while retaining gaze estimation. In this paper, we present an algorithm to add “snow” to the eye image and evaluate the privacy-utility tradeoff for the choice of noise parameter.
Topics & Concepts
Computer scienceSpoofing attackIRIS (biosensor)Computer visionPixelNoise (video)Artificial intelligenceGazeIdentity (music)Authentication (law)Iris recognitionSignature (topology)BitTorrent trackerBiometricsSnowEye trackingComputer securityImage (mathematics)GeographyMathematicsMeteorologyPhysicsGeometryAcousticsBiometric Identification and SecurityGaze Tracking and Assistive TechnologyUser Authentication and Security Systems