An Empirical Study of DNNs Robustification Inefficacy in Protecting Visual Recommenders

Vito Walter Anelli
Vito Walter Anelli
Daniele Malitesta
Daniele Malitesta
Felice Antonio Merra
Felice Antonio Merra
Cited by: 0|Bibtex|Views1|Links

Abstract:

Visual-based recommender systems (VRSs) enhance recommendation performance by integrating users' feedback with the visual features of product images extracted from a deep neural network (DNN). Recently, human-imperceptible images perturbations, defined \textit{adversarial attacks}, have been demonstrated to alter the VRSs recommendation...More

Code:

Data:

Your rating :
0

 

Tags
Comments