Search Results for author:
Found 3 papers, 0 papers with code
Fuzzy Commitments Offer Insufficient Protection to Biometric Templates Produced by Deep Learning
Even in the "hardest" settings (in which we take a reconstructed image from one system and use it in a different system, with different feature extraction process) the reconstructed image offers 50 to 120 times higher success rates than the system's FAR.
A Simple Explanation for the Existence of Adversarial Examples with Small Hamming Distance
The existence of adversarial examples in which an imperceptible change in the input can fool well trained neural networks was experimentally discovered by Szegedy et al in 2013, who called them "Intriguing properties of neural networks".
HoneyFaces: Increasing the Security and Privacy of Authentication Using Synthetic Facial Images
We implemented the HoneyFaces system and tested it with a password file composed of 270 real users.
