DeepAI AI Chat

Towards Explaining Adversarial Examples Phenomenon in Artificial Neural Networks

07/22/2021

∙

by Ramin Barati, et al.

∙

AUT

∙

∙

In this paper, we study the adversarial examples existence and adversarial training from the standpoint of convergence and provide evidence that pointwise convergence in ANNs can explain these observations. The main contribution of our proposal is that it relates the objective of the evasion attacks and adversarial training with concepts already defined in learning theory. Also, we extend and unify some of the other proposals in the literature and provide alternative explanations on the observations made in those proposals. Through different experiments, we demonstrate that the framework is valuable in the study of the phenomenon and is applicable to real-world problems.

Ramin Barati
2 publications
Reza Safabakhsh
11 publications
Mohammad Rahmati
12 publications

∙ 05/26/2022

An Analytic Framework for Robust Training of Artificial Neural Networks

The reliability of a learning model is key to the successful deployment ...

0 Ramin Barati, et al. ∙

∙ 12/20/2014

Explaining and Harnessing Adversarial Examples

Several machine learning models, including neural networks, consistently...

0 Ian J. Goodfellow, et al. ∙

∙ 05/23/2022

Collaborative Adversarial Training

The vulnerability of deep neural networks (DNNs) to adversarial examples...

0 Qizhang Li, et al. ∙

∙ 01/26/2016

Unifying Adversarial Training Algorithms with Flexible Deep Data Gradient Regularization

Many previous proposals for adversarial training of deep neural nets hav...

0 Alexander G. Ororbia II, et al. ∙

∙ 09/21/2022

Toy Models of Superposition

Neural networks often pack many unrelated concepts into a single neuron ...

12 Nelson Elhage, et al. ∙

∙ 11/09/2019

Adaptive versus Standard Descent Methods and Robustness Against Adversarial Examples

Adversarial examples are a pervasive phenomenon of machine learning mode...

12 Marc Khoury, et al. ∙