Adversarial Machine Learning against Modern Behavioral Biometrics Systems

Closed captioning will be available in English and Japanese for all keynotes and RSAC track sessions.
Please note: All times are in SGT.
  1. Moscone West

As authentication systems increasingly embrace behavioral attributes enhanced using machine learning to continuously authenticate and implicitly identify users, attackers are countering using machine learning–based adversarial attacks to combat such defenses. This session will walk through such novel attacks and how a modern corporation can implement countermeasures and defensive techniques.

Learning Objectives:
1: Observe traditional multifactor authentication against newer behavioral biometric authentication.
2: Learn how machine and deep learning are increasingly being used by attackers against such systems.
3: Learn how to mitigate the risk and prevent such advanced attacks targeting these behavioral models.

Participants should be aware of how modern authentication systems work and a general understanding of machine learning–based concepts.

Download pdf