Towards Explaining Adversarial Examples Phenomenon in Artificial Neural Networks
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Learning TheorySimilar Papers 제목 키워드 기반
Explaining and Harnessing Adversarial Examples
Several machine learning models, including neural networks, consistently misclassify adversarial examples---inputs formed by applying small but intentionally worst-case perturbations to examples from the dataset, such th…
Image ClassificationAn Analytic Framework for Robust Training of Artificial Neural Networks
The reliability of a learning model is key to the successful deployment of machine learning in various industries. Creating a robust model, particularly one unaffected by adversarial attacks, requires a comprehensive und…
Learning TheoryOn The Relationship Between Universal Adversarial Attacks And Sparse Representations
The prominent success of neural networks, mainly in computer vision tasks, is increasingly shadowed by their sensitivity to small, barely perceivable adversarial perturbations in image input. In this work, we aim at expl…
SensitivityVerifying the Causes of Adversarial Examples
The robustness of neural networks is challenged by adversarial examples that contain almost imperceptible perturbations to inputs, which mislead a classifier to incorrect outputs in high confidence. Limited by the extrem…
Density EstimationAnalyzing the Noise Robustness of Deep Neural Networks
Deep neural networks (DNNs) are vulnerable to maliciously generated adversarial examples. These examples are intentionally designed by making imperceptible perturbations and often mislead a DNN into making an incorrect p…