Atgan: Adversarial training-based gan for improving adversarial robustness generalization on image classification
D Wang, W Jin, Y Wu, A Khan - Applied Intelligence, 2023 - Springer
Deep neural networks are vulnerable to adversarial examples, which are well-designed
examples aiming to cause models to produce wrong outputs with high confidence. Although …
examples aiming to cause models to produce wrong outputs with high confidence. Although …
Improving global adversarial robustness generalization with adversarially trained GAN
Convolutional neural networks (CNNs) have achieved beyond human-level accuracy in the
image classification task and are widely deployed in real-world environments. However …
image classification task and are widely deployed in real-world environments. However …
Between-Class Adversarial Training for Improving Adversarial Robustness of Image Classification
D Wang, W Jin, Y Wu - Sensors, 2023 - mdpi.com
Deep neural networks (DNNs) have been known to be vulnerable to adversarial attacks.
Adversarial training (AT) is, so far, the only method that can guarantee the robustness of …
Adversarial training (AT) is, so far, the only method that can guarantee the robustness of …
How to compare adversarial robustness of classifiers from a global perspective
Adversarial robustness of machine learning models has attracted considerable attention
over recent years. Adversarial attacks undermine the reliability of and trust in machine …
over recent years. Adversarial attacks undermine the reliability of and trust in machine …
K Minimum Enclosing Balls for Outlier Detection
D Staps, T Villmann, B Paaßen - International Workshop on Self …, 2024 - Springer
Outlier detection means to characterize the distribution of inliers exactly enough such that
outliers stand out. A natural and interpretable model is an enclosing ball that includes non …
outliers stand out. A natural and interpretable model is an enclosing ball that includes non …
K Minimum Enclosing Balls for Outlier
D Staps, T Villmann¹, B Paaßen - Advances in Self-Organizing …, 2024 - books.google.com
Outlier detection means to characterize the distribution of inliers exactly enough such that
outliers stand out. A natural and inter-pretable model is an enclosing ball that includes non …
outliers stand out. A natural and inter-pretable model is an enclosing ball that includes non …
Intelligent anomaly detection in the manufacturing of kitchen cabinets
S Lakshminarayanan - 2024 - diva-portal.org
Anomaly detection within manufacturing processes is critical for ensuring product quality
and customer satisfaction. In this study, we explore the possibility of employing an efficient …
and customer satisfaction. In this study, we explore the possibility of employing an efficient …
A general framework for defining and optimizing robustness
Robustness of neural networks has recently attracted a great amount of interest. The many
investigations in this area lack a precise common foundation of robustness concepts …
investigations in this area lack a precise common foundation of robustness concepts …