Machine Learning Model Attribution Challenge

no code implementations • 13 Feb 2023 • Elizabeth Merkhofer, Deepesh Chaudhari, Hyrum S. Anderson, Keith Manville, Lily Wong, João Gante

We present the findings of the Machine Learning Model Attribution Challenge.

Attribute

Adversarial Attack Attribution: Discovering Attributable Signals in Adversarial ML Attacks

no code implementations • 8 Jan 2021 • Marissa Dotter, Sherry Xie, Keith Manville, Josh Harguess, Colin Busho, Mikel Rodriguez

In other words, is there a way to find a signal in these attacks that exposes the attack algorithm, model architecture, or hyperparameters used in the attack?

Adversarial Attack Attribute +1

APRICOT: A Dataset of Physical Adversarial Attacks on Object Detection

1 code implementation • ECCV 2020 • A. Braunegg, Amartya Chakraborty, Michael Krumdick, Nicole Lape, Sara Leary, Keith Manville, Elizabeth Merkhofer, Laura Strickhart, Matthew Walmer

Physical adversarial attacks threaten to fool object detection systems, but reproducible research on the real-world effectiveness of physical patches and how to defend against them requires a publicly available benchmark dataset.

Adversarial Robustness Density Estimation +2

Overhead Detection: Beyond 8-bits and RGB

no code implementations • 7 Aug 2018 • Eliza Mace, Keith Manville, Monica Barbu-McInnis, Michael Laielli, Matthew Klaric, Samuel Dooley

Specifically, we examine how various features of the data affect building detection accuracy with respect to the Intersection over Union metric.