Adversarial Doodles: Interpretable and Human-drawable Attacks Provide Describable Insights

27 November 2023

Papers citing "Adversarial Doodles: Interpretable and Human-drawable Attacks Provide Describable Insights"

2 / 2 papers shown

Title
Robust Feature-Level Adversaries are Interpretability Tools Stephen Casper Max Nadeau Dylan Hadfield-Menell Gabriel Kreiman AAML 40 27 0 07 Oct 2021
Adversarial Camouflage: Hiding Physical-World Attacks with Natural Styles Ranjie Duan Xingjun Ma Yisen Wang James Bailey •. A. K. Qin Yun Yang AAML 154 224 0 08 Mar 2020