Evaluating Deep Learning Models and Adversarial Attacks on Accelerometer-Based Gesture Authentication

no code implementations • 3 Oct 2021 • Elliu Huang, Fabio Di Troia, Mark Stamp

Although prior research has shown that deep learning models are vulnerable to adversarial attacks, relatively little research has been done in the adversarial domain for behavioral biometrics.

Adversarial Attack BIG-bench Machine Learning +1