On The Detection Of Adversarial Attacks Through Reliable AI
- Resource Type
- Conference
- Authors
- Vaccari, Ivan; Carlevaro, Alberto; Narteni, Sara; Cambiaso, Enrico; Mongelli, Maurizio
- Source
- IEEE INFOCOM 2022 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) Computer Communications Workshops (INFOCOM WKSHPS), IEEE INFOCOM 2022 - IEEE Conference on. :1-6 May, 2022
- Subject
- Communication, Networking and Broadcast Technologies
Machine learning algorithms
Conferences
Adversarial machine learning
Reliability
Artificial intelligence
machine learning
detection algorithms
adversarial machine learning
reliable
- Language
Adversarial machine learning manipulates datasets to mislead machine learning algorithm decisions. We propose a new approach able to detect adversarial attacks, based on eXplainable and Reliable AI. The results obtained show how canonical algorithms may have difficulty in identifying attacks, while the proposed approach is able to correctly identify different adversarial settings.