4 citations · 4 across the 3 of their papers we have counts for
4 papers
Automating Defense Against Adversarial Attacks: Discovery of Vulnerabilities and Application of Multi-INT Imagery to Protect Deployed Models
Josh Kalin, David Noever, Matthew Ciolino +2
Image classification is a common step in image recognition for machine learning in overhead applications. When applying popular model architectures like MobileNetV2, known vulnerab…
Local Translation Services for Neglected Languages
David Noever, Josh Kalin, Matt Ciolino +2
Taking advantage of computationally lightweight, but high-quality translators prompt consideration of new applications that address neglected languages. Locally run translators for…
Black Box to White Box: Discover Model Characteristics Based on Strategic Probing
Josh Kalin, Matthew Ciolino, David Noever +1
In Machine Learning, White Box Adversarial Attacks rely on knowing underlying knowledge about the model attributes. This works focuses on discovering to distrinct pieces of model i…
Systematic Attack Surface Reduction For Deployed Sentiment Analysis Models
Josh Kalin, David Noever, Gerry Dozier
This work proposes a structured approach to baselining a model, identifying attack vectors, and securing the machine learning models after deployment. This method for securing each…