1 code implementation • 21 Nov 2023 • Marco Anisetti, Claudio A. Ardagna, Nicola Bena, Ernesto Damiani, Paolo G. Panero
Our solution goes beyond the state of the art by providing an architectural and methodological approach that continuously guarantees a stable non-functional behavior of ML-based applications, is applicable to different ML models, and is driven by non-functional properties assessed on the models themselves.
no code implementations • 26 May 2023 • Marco Anisetti, Claudio A. Ardagna, Nicola Bena, Ernesto Damiani
Machine Learning (ML) is increasingly used to implement advanced applications with non-deterministic behavior, which operate on the cloud-edge continuum.
no code implementations • 17 Jan 2023 • Zhibo Zhang, Sani Umar, Ahmed Y. Al Hammadi, Sangyoung Yoon, Ernesto Damiani, Claudio Agostino Ardagna, Nicola Bena, Chan Yeob Yeun
The major aim of this paper is to explain the data poisoning attacks using label-flipping during the training stage of the electroencephalogram (EEG) signal-based human emotion evaluation systems deploying Machine Learning models from the attackers' perspective.
1 code implementation • 28 Sep 2022 • Marco Anisetti, Claudio A. Ardagna, Alessandro Balestrucci, Nicola Bena, Ernesto Damiani, Chan Yeob Yeun
This huge progress in terms of prediction quality does not however find a counterpart in the security of such models and corresponding predictions, where perturbations of fractions of the training set (poisoning) can seriously undermine the model accuracy.