375 citations · 548 across the 11 of their papers we have counts for
Showing stat.MLShow all
2 papers · 1 filter
stat.ML2018★ 45 cited
Defending against Adversarial Images using Basis Functions Transformations
Uri Shaham, James Garritano, Yutaro Yamada +5
We study the effectiveness of various approaches that defend against adversarial attacks on deep networks via manipulations based on basis function representations of images. Speci…
stat.ML2015★ 375 cited
Understanding Adversarial Training: Increasing Local Stability of Neural Nets through Robust Optimization
Uri Shaham, Yutaro Yamada, Sahand Negahban
We propose a general framework for increasing local stability of Artificial Neural Nets (ANNs) using Robust Optimization (RO). We achieve this through an alternating minimization-m…