4 citations · 4 across the 3 of their papers we have counts for
3 papers
Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition
Sander Schulhoff, Jeremy Pinto, Anaum Khan +7
Large Language Models (LLMs) are deployed in interactive contexts with direct user engagement, such as chatbots and writing assistants. These deployments are vulnerable to prompt i…
Coloring Deep CNN Layers with Activation Hue Loss
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},…
U(1) Symmetry-breaking Observed in Generic CNN Bottleneck Layers
Louis-François Bouchard, Mohsen Ben Lazreg, Matthew Toews
We report on a novel model linking deep convolutional neural networks (CNN) to biological vision and fundamental particle physics. Information propagation in a CNN is modeled via a…