Biologically Inspired Mechanisms for Adversarial Robustness
A convolutional neural network strongly robust to adversarial perturbations at reasonable computational and performance cost has not yet been demonstrated. The primate visual ventral stream seems to be robust to small perturbations in visual stimuli but the underlying mechanisms that give rise to th...
Main Authors: | Vuyyuru Reddy, Manish, Banburski, Andrzej, Plant, Nishka, Poggio, Tomaso |
---|---|
Format: | Technical Report |
Published: |
Center for Brains, Minds and Machines (CBMM)
2020
|
Online Access: | https://hdl.handle.net/1721.1/125981 |
Similar Items
-
PCA as a defense against some adversaries
by: Aparne, Gupta, et al.
Published: (2022) -
Cross-validation Stability of Deep Networks
by: Banburski, Andrzej, et al.
Published: (2021) -
An Overview of Some Issues in the Theory of Deep Networks
by: Poggio, Tomaso, et al.
Published: (2022) -
An Overview of Some Issues in the Theory of Deep Networks
by: Poggio, Tomaso, et al.
Published: (2021) -
The Effects of Image Distribution and Task on Adversarial Robustness
by: Kunhardt, Owen, et al.
Published: (2021)