Home > Research > Publications & Outputs > UNICAD: A Unified Approach for Attack Detection...

Electronic data

  • UNICAD

    Accepted author manuscript, 894 KB, PDF document

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

Forthcoming
Publication date15/03/2024
Host publication2024 International Joint Conference on Neural Networks (IJCNN)
PublisherIEEE
Number of pages8
<mark>Original language</mark>English
EventInternational Joint Conference on Neural Networks 2024: IEEE WCCI (IJCNN) 2024 - Yokohama, Japan
Duration: 30/06/20245/07/2024
https://2024.ieeewcci.org

Conference

ConferenceInternational Joint Conference on Neural Networks 2024
Abbreviated titleIEEE WCCI IJCNN 2024
Country/TerritoryJapan
CityYokohama
Period30/06/245/07/24
Internet address

Conference

ConferenceInternational Joint Conference on Neural Networks 2024
Abbreviated titleIEEE WCCI IJCNN 2024
Country/TerritoryJapan
CityYokohama
Period30/06/245/07/24
Internet address

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’s effectiveness in adver- sarial mitigation and unseen class classification, outperforming traditional models.