From Notices of the AMS
An Analytical and Geometric Perspective on Adversarial Robustness
by Nicolás García Trillos
Communicated by Matt Jacobs
"…y luego se fueron el uno para el otro, como si fueran dos mortales enemigos. " Miguel de Cervantes, Don Quixote; Chapter 8, Part 1.
1. Introduction
In the last ten years, neural networks have made incredible strides in classifying large data sets, to the point that they can now outperform humans in raw accuracy. However, the robustness of these systems is a completely different story. Suppose you were asked to identify whether a photo contained an image of a cat or a dog. You probably would have no difficulty at all; at worst, maybe you would only be tripped up by a particularly small or unusual Shiba Inu. In contrast, it has been widely documented that an adversary can convince an otherwise well-performing neural network that a dog is actually a cat (or vice-versa) by making tiny human-imperceptible changes to an image at the pixel level. These small perturbations are known as adversarial attacks and they are a significant obstacle to the deployment of machine learning systems in security-critical applications [GSS14]. The susceptibility to adversarial attacks is not exclusive to neural network models, and many other learning systems have also been observed to be brittle when facing adversarial perturbations of data.
- Also in Notices
- Aperiodic Tilings, Order, and Randomness
- Persistence Over Posets
