research
∙
01/08/2023
Facial Misrecognition Systems: Simple Weight Manipulations Force DNNs to Err Only on Specific Persons
In this paper we describe how to plant novel types of backdoors in any f...
share
research
∙
06/18/2021
The Dimpled Manifold Model of Adversarial Examples in Machine Learning
The extreme fragility of deep neural networks when presented with tiny p...
research
∙
08/09/2020
Consistent High Dimensional Rounding with Side Information
In standard rounding, we want to map each value X in a large continuous ...
research
∙
01/30/2019
A Simple Explanation for the Existence of Adversarial Examples with Small Hamming Distance
The existence of adversarial examples in which an imperceptible change i...
research
∙
01/09/2018