Visible to the public Securing Safety-Critical Machine Learning Algorithms - October 2021Conflict Detection Enabled

PI(s), Co-PI(s), Researchers: Lujo Bauer, Matt Fredrikson (CMU), Mike Reiter (UNC)

HARD PROBLEM(S) ADDRESSED

This project addresses the following hard problems: developing security metrics and developing resilient architectures. Both problems are tackled in the context of deep neural networks, which are a particularly popular and performant type of machine learning algorithm. This project develops metrics that characterize the degree to which a neural-network-based classifier can be evaded through practically realizable, inconspicuous attacks. The project also develops architectures for neural networks that would make them robust to adversarial examples.

PUBLICATIONS

N/A this quarter

PUBLIC ACCOMPLISHMENT HIGHLIGHTS

No new data

COMMUNITY ENGAGEMENTS (If applicable)

Reiter presented "Beyond lp Balls: Attacks on Real-world Uses of Machine Learning", at the lablet meeting on Jul. 13, 2021.

Bauer participated in the International School on Foundations of Security Analysis and Design (FOSAD), in Bertinoro, Italy, and presented "Attacks on real-world uses of machine learning", which included content developed as part of this award. Sep. 2-3, 2021.

EDUCATIONAL ADVANCES (If applicable)

N/A this quarter