Home > Research > Publications & Outputs > UNICAD

Electronic data

  • UNICAD

    Accepted author manuscript, 894 KB, PDF document

Links

Text available via DOI:

View graph of relations

UNICAD: A Unified Approach for Attack Detection, Noise Reduction and Novel Class Identification

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

UNICAD: A Unified Approach for Attack Detection, Noise Reduction and Novel Class Identification. / Lopez Pellicer, Alvaro; Giatgong, Kittipos; Li, Yi et al.
2024 International Joint Conference on Neural Networks (IJCNN). IEEE, 2024.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Lopez Pellicer, A, Giatgong, K, Li, Y, Suri, N & Angelov, P 2024, UNICAD: A Unified Approach for Attack Detection, Noise Reduction and Novel Class Identification. in 2024 International Joint Conference on Neural Networks (IJCNN). IEEE, International Joint Conference on Neural Networks 2024, Yokohama, Japan, 30/06/24. https://doi.org/10.1109/IJCNN60899.2024.10651159

APA

Vancouver

Lopez Pellicer A, Giatgong K, Li Y, Suri N, Angelov P. UNICAD: A Unified Approach for Attack Detection, Noise Reduction and Novel Class Identification. In 2024 International Joint Conference on Neural Networks (IJCNN). IEEE. 2024 Epub 2024 Jun 30. doi: 10.1109/IJCNN60899.2024.10651159

Author

Lopez Pellicer, Alvaro ; Giatgong, Kittipos ; Li, Yi et al. / UNICAD : A Unified Approach for Attack Detection, Noise Reduction and Novel Class Identification. 2024 International Joint Conference on Neural Networks (IJCNN). IEEE, 2024.

Bibtex

@inproceedings{458abc323f574511b2213ed93c779ab1,
title = "UNICAD: A Unified Approach for Attack Detection, Noise Reduction and Novel Class Identification",
abstract = "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{\textquoteright}s effectiveness in adver- sarial mitigation and unseen class classification, outperforming traditional models.",
author = "{Lopez Pellicer}, Alvaro and Kittipos Giatgong and Yi Li and Neeraj Suri and Plamen Angelov",
year = "2024",
month = sep,
day = "9",
doi = "10.1109/IJCNN60899.2024.10651159",
language = "English",
isbn = "9798350359329",
booktitle = "2024 International Joint Conference on Neural Networks (IJCNN)",
publisher = "IEEE",
note = "International Joint Conference on Neural Networks 2024 : IEEE WCCI (IJCNN) 2024, IEEE WCCI IJCNN 2024 ; Conference date: 30-06-2024 Through 05-07-2024",
url = "https://2024.ieeewcci.org",

}

RIS

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 -