no code implementations • 15 Mar 2024 • Tobias Leemann, Martin Pawelczyk, Bardh Prenkaj, Gjergji Kasneci
We subsequently investigate how different components in the objective functions, e. g., the machine learning model or cost function used to measure distance, determine whether the outcome can be considered an adversarial example or not.
no code implementations • 18 Dec 2023 • Mario Alfonso Prado-Romero, Bardh Prenkaj, Giovanni Stilo
Counterfactual Explanation (CE) techniques have garnered attention as a means to provide insights to the users engaging with AI systems.
1 code implementation • 4 Aug 2023 • Bardh Prenkaj, Mario Villaizan-Vallelado, Tobias Leemann, Gjergji Kasneci
The GAEs minimise the reconstruction error between the original graph and its learned representation during training.
1 code implementation • ICCV 2023 • Alessandro Flaborea, Luca Collorone, Guido D'Amely, Stefano D'arrigo, Bardh Prenkaj, Fabio Galasso
Leading OCC techniques constrain the latent representations of normal motions to limited volumes and detect as abnormal anything outside, which accounts satisfactorily for the openset'ness of anomalies.
Ranked #1 on Video Anomaly Detection on HR-UBnormal
1 code implementation • 13 Feb 2023 • Bardh Prenkaj, Paola Velardi
Real-time monitoring of human behaviours, especially in e-Health applications, has been an active area of research in the past decades.
no code implementations • 1 Feb 2023 • Luca Podo, Bardh Prenkaj, Paola Velardi
Visualization Recommendation Systems (VRSs) are a novel and challenging field of study aiming to help generate insightful visualizations from data and support non-expert users in information discovery.
1 code implementation • 16 Nov 2022 • Alessandro Flaborea, Bardh Prenkaj, Bharti Munjal, Marco Aurelio Sterpa, Dario Aragona, Luca Podo, Fabio Galasso
By using uncertainty, HypAD may assess whether it is certain about the input signal but it fails to reconstruct it because this is anomalous; or whether the reconstruction error does not necessarily imply anomaly, as the model is uncertain, e. g. a complex but regular input signal.
1 code implementation • 21 Oct 2022 • Mario Alfonso Prado-Romero, Bardh Prenkaj, Giovanni Stilo, Fosca Giannotti
Due to the growing attention in graph learning, we focus on the concepts of CE for GNNs.
1 code implementation • 22 Oct 2019 • Hamed Sarvari, Carlotta Domeniconi, Bardh Prenkaj, Giovanni Stilo
Autoencoders, as a dimensionality reduction technique, have been recently applied to outlier detection.