A Study of Robustness of Neural Nets Using Approximate Feature Collisions

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness (2019, methodology): “In the following, we build on existing invariance-based attacks (Jacobsen et al., 2019; Behrmann et al., 2018; Li et al., 2019) to propose a model-agnostic algorithm for crafting invariance-based adversarial examples.”