2 code implementations • 24 Oct 2023 • Sander Schulhoff, Jeremy Pinto, Anaum Khan, Louis-François Bouchard, Chenglei Si, Svetlina Anati, Valen Tagliabue, Anson Liu Kost, Christopher Carnahan, Jordan Boyd-Graber
We also present a comprehensive taxonomical ontology of the types of adversarial prompts.
no code implementations • 5 Oct 2023 • Louis-François Bouchard, Mohsen Ben Lazreg, Matthew Toews
This paper proposes a novel hue-like angular parameter to model the structure of deep convolutional neural network (CNN) activation space, referred to as the {\em activation hue}, for the purpose of regularizing models for more effective learning.
no code implementations • 5 Jun 2022 • Louis-François Bouchard, Mohsen Ben Lazreg, Matthew Toews
A 3D space $(x, y, t)$ is defined by $(x, y)$ coordinates in the image plane and CNN layer $t$, where a principal ray $(0, 0, t)$ runs in the direction of information propagation through both the optical axis and the image center pixel located at $(x, y)=(0, 0)$, about which the sharpest possible spatial focus is limited to a circle of confusion in the image plane.