Towards Explaining Adversarial Examples Phenomenon in Artificial Neural Networks
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 11 of its 12 references that are in the map. First posted on arXiv 22 Jul 2021.
Builds on
11 of 12 references.
References · 11
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2013Intriguing properties of neural networkscited by 5,114
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
- 2016Adversarial examples in the physical worldcited by 1,762
- 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
- 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
- 2018Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hidingcited by 83
- 2016A Boundary Tilting Persepective on the Phenomenon of Adversarial Examplescited by 70
- 2019A Simple Explanation for the Existence of Adversarial Examples with Small Hamming Distancecited by 32
- 2015Exploring the Space of Adversarial Imagescited by 28
- 2019Simple Physical Adversarial Examples against End-to-End Autonomous Driving Modelscited by 17
Built on by
Citing papers per year: 2022: 1.
1 paper.