Black Box to White Box: Discover Model Characteristics Based on Strategic Probing

7 September 2020

Papers citing "Black Box to White Box: Discover Model Characteristics Based on Strategic Probing"

4 / 4 papers shown

Title
An Auditing Test To Detect Behavioral Shift in Language Models Leo Richter Xuanli He Pasquale Minervini Matt J. Kusner 88 0 0 25 Oct 2024
Automating Defense Against Adversarial Attacks: Discovery of Vulnerabilities and Application of Multi-INT Imagery to Protect Deployed Models Josh Kalin David Noever Matthew Ciolino Dom Hambrick Gerry V. Dozier AAML 194 1 0 29 Mar 2021
Reading Isn't Believing: Adversarial Attacks On Multi-Modal Neurons David Noever S. M. Noever AAML VLM 93 35 0 18 Mar 2021
Fortify Machine Learning Production Systems: Detect and Classify Adversarial Attacks Matthew Ciolino Josh Kalin David Noever AAML 189 2 0 19 Feb 2021