Visually-aware recommendation leverages visual signals of product images extracted through Deep Neural Networks to improve the recommendation performance. However, human-imperceptible adversarial noise can alter recommendation outcomes, e.g., pushing/nuking specific product categories. In this work, we provide 24 combinations of attack/defense strategies, and visual-based recommenders to 1) access performance alteration on recommendation and 2) empirically verify the effect on final users through offline-visual metrics. The results suggest defense is not protecting recommender models as expected, and shed light on the importance of human evaluation to identify visual attacks on recommendations. Source code, data, and experimental parameters are available at https://github.com/sisinflab/ Perceptual-Rec-Mutation-of-Adv-VRs.

Assessing perceptual and recommendation mutation of adversarially-poisoned visual recommenders / Anelli, Vito Walter; Di Noia, Tommaso; Malitesta, Daniele; Merra, Felice Antonio. - ELETTRONICO. - 2776:(2020), pp. 49-56. (Intervento presentato al convegno AIxIA Discussion Papers Workshop, AIxIA 2020 DP tenutosi a Virtual nel November 27th, 2020).

Assessing perceptual and recommendation mutation of adversarially-poisoned visual recommenders

Vito Walter Anelli;Tommaso Di Noia;Daniele Malitesta;Felice Antonio Merra
2020-01-01

Abstract

Visually-aware recommendation leverages visual signals of product images extracted through Deep Neural Networks to improve the recommendation performance. However, human-imperceptible adversarial noise can alter recommendation outcomes, e.g., pushing/nuking specific product categories. In this work, we provide 24 combinations of attack/defense strategies, and visual-based recommenders to 1) access performance alteration on recommendation and 2) empirically verify the effect on final users through offline-visual metrics. The results suggest defense is not protecting recommender models as expected, and shed light on the importance of human evaluation to identify visual attacks on recommendations. Source code, data, and experimental parameters are available at https://github.com/sisinflab/ Perceptual-Rec-Mutation-of-Adv-VRs.
2020
AIxIA Discussion Papers Workshop, AIxIA 2020 DP
Assessing perceptual and recommendation mutation of adversarially-poisoned visual recommenders / Anelli, Vito Walter; Di Noia, Tommaso; Malitesta, Daniele; Merra, Felice Antonio. - ELETTRONICO. - 2776:(2020), pp. 49-56. (Intervento presentato al convegno AIxIA Discussion Papers Workshop, AIxIA 2020 DP tenutosi a Virtual nel November 27th, 2020).
File in questo prodotto:
File Dimensione Formato  
paper-6.pdf

accesso aperto

Tipologia: Versione editoriale
Licenza: Creative commons
Dimensione 956.28 kB
Formato Adobe PDF
956.28 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11589/216141
Citazioni
  • Scopus 5
  • ???jsp.display-item.citation.isi??? ND
social impact