Add to ORKGReliable deployment of machine learning models such as neural networks continues to be challenging due to several limitations. Some of the main shortcomings are the lack of interpretability and the lack of robustness against adversarial examples or out-of-distribution inputs. In this paper, we explore the possibilities and limits of adversarial attacks for explainable machine learning models. First, we extend the notion of adversarial examples to fit in explainable machine learning scenarios, in which the inputs, the output classifications and the explanations of the model's decisions are assessed by humans. Next, we propose a comprehensive framework to study whether (and how) adversarial examples can be generated for explainable models und...
Despite AI and Neural Networks model had an overwhelming evolution during the past decade, their app...
Machine Learning algorithms provide astonishing performance in a wide range of tasks, including sens...
Recent research has shown Deep Neural Networks (DNNs) to be vulnerable to adversarial examples that ...
In recent years, the topic of explainable machine learning (ML) has been extensively researched. Up ...
In spite of the successful application in many fields, machine learning models today suffer from not...
The robustness of neural networks is challenged by adversarial examples that contain almost impercep...
In recent years, machine learning (ML) models have been extensively used in software analytics, such...
Pattern recognition systems based on machine learning techniques are nowadays widely used in many di...
In this paper, we study the adversarial examples existence and adversarial training from the standpo...
Methods for model explainability have become increasingly critical for testing the fairness and soun...
Recent advances in Machine Learning (ML) have profoundly changed many detection, classification, rec...
Modern machine learning models can be difficult to probe and understand after they have been trained...
The literature on adversarial attacks in computer vision typically focuses on pixel-level perturbati...
Despite the remarkable performance and generalization levels of deep learning models in a wide range...
Explainability has been widely stated as a cornerstone of the responsible and trustworthy use of mac...
Despite AI and Neural Networks model had an overwhelming evolution during the past decade, their app...
Machine Learning algorithms provide astonishing performance in a wide range of tasks, including sens...
Recent research has shown Deep Neural Networks (DNNs) to be vulnerable to adversarial examples that ...
In recent years, the topic of explainable machine learning (ML) has been extensively researched. Up ...
In spite of the successful application in many fields, machine learning models today suffer from not...
The robustness of neural networks is challenged by adversarial examples that contain almost impercep...
In recent years, machine learning (ML) models have been extensively used in software analytics, such...
Pattern recognition systems based on machine learning techniques are nowadays widely used in many di...
In this paper, we study the adversarial examples existence and adversarial training from the standpo...
Methods for model explainability have become increasingly critical for testing the fairness and soun...
Recent advances in Machine Learning (ML) have profoundly changed many detection, classification, rec...
Modern machine learning models can be difficult to probe and understand after they have been trained...
The literature on adversarial attacks in computer vision typically focuses on pixel-level perturbati...
Despite the remarkable performance and generalization levels of deep learning models in a wide range...
Explainability has been widely stated as a cornerstone of the responsible and trustworthy use of mac...
Despite AI and Neural Networks model had an overwhelming evolution during the past decade, their app...
Machine Learning algorithms provide astonishing performance in a wide range of tasks, including sens...
Recent research has shown Deep Neural Networks (DNNs) to be vulnerable to adversarial examples that ...