Accepted author manuscript, 894 KB, PDF document
Final published version
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
}
TY - GEN
T1 - UNICAD
T2 - International Joint Conference on Neural Networks 2024
AU - Lopez Pellicer, Alvaro
AU - Giatgong, Kittipos
AU - Li, Yi
AU - Suri, Neeraj
AU - Angelov, Plamen
PY - 2024/9/9
Y1 - 2024/9/9
N2 - As the use of Deep Neural Networks (DNNs) be- comes pervasive, their vulnerability to adversarial attacks and limitations in handling unseen classes poses significant challenges. The state-of-the-art offers discrete solutions aimed to tackle individual issues covering specific adversarial attack scenarios, classification or evolving learning. However, real-world systems need to be able to detect and recover from a wide range of adversarial attacks without sacrificing classification accuracy and to flexibly act in unseen scenarios. In this paper, UNICAD, is proposed as a novel framework that integrates a variety of techniques to provide an adaptive solution.For the targeted image classification, UNICAD is able to provide accurate image classification while still handling un- seen scenarios by detecting unseen classes and detecting and recovering adversarially attacked inputs. This has been achieved by leveraging Prototype and Similarity-based DNNs, along with denoising autoencoders. Our experiments performed on the CIFAR-10 dataset highlight UNICAD’s effectiveness in adver- sarial mitigation and unseen class classification, outperforming traditional models.
AB - As the use of Deep Neural Networks (DNNs) be- comes pervasive, their vulnerability to adversarial attacks and limitations in handling unseen classes poses significant challenges. The state-of-the-art offers discrete solutions aimed to tackle individual issues covering specific adversarial attack scenarios, classification or evolving learning. However, real-world systems need to be able to detect and recover from a wide range of adversarial attacks without sacrificing classification accuracy and to flexibly act in unseen scenarios. In this paper, UNICAD, is proposed as a novel framework that integrates a variety of techniques to provide an adaptive solution.For the targeted image classification, UNICAD is able to provide accurate image classification while still handling un- seen scenarios by detecting unseen classes and detecting and recovering adversarially attacked inputs. This has been achieved by leveraging Prototype and Similarity-based DNNs, along with denoising autoencoders. Our experiments performed on the CIFAR-10 dataset highlight UNICAD’s effectiveness in adver- sarial mitigation and unseen class classification, outperforming traditional models.
U2 - 10.1109/IJCNN60899.2024.10651159
DO - 10.1109/IJCNN60899.2024.10651159
M3 - Conference contribution/Paper
SN - 9798350359329
BT - 2024 International Joint Conference on Neural Networks (IJCNN)
PB - IEEE
Y2 - 30 June 2024 through 5 July 2024
ER -