The last decade has witnessed a massive deployment of Machine Learning tools in everyday life automated tasks. Neural Networks are nowadays in use in a growing number of application areas because of their excellent performances. Unfortunately, it has been shown by many researchers that they can be attacked and fooled in several different ways, and this can dangerously impair their ability to correctly perform their tasks. In this paper we describe a watermarking algorithm that can protect and verify the integrity of (Deep) Neural Networks when deployed in safety critical systems, such as autonomous driving systems or monitoring and surveillance systems.

NeuNAC: A novel fragile watermarking algorithm for integrity protection of neural networks

Botta M.
;
Cavagnino D.;Esposito R.
2021-01-01

Abstract

The last decade has witnessed a massive deployment of Machine Learning tools in everyday life automated tasks. Neural Networks are nowadays in use in a growing number of application areas because of their excellent performances. Unfortunately, it has been shown by many researchers that they can be attacked and fooled in several different ways, and this can dangerously impair their ability to correctly perform their tasks. In this paper we describe a watermarking algorithm that can protect and verify the integrity of (Deep) Neural Networks when deployed in safety critical systems, such as autonomous driving systems or monitoring and surveillance systems.
2021
576
228
241
https://doi.org/10.1016/j.ins.2021.06.073
Deep neural network; Fragile watermarking; Integrity protection; Linear transformation
Botta M.; Cavagnino D.; Esposito R.
File in questo prodotto:
File Dimensione Formato  
1-s2.0-S0020025521006642-main.pdf

Accesso aperto

Descrizione: Articolo completo
Tipo di file: PDF EDITORIALE
Dimensione 929.25 kB
Formato Adobe PDF
929.25 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/2318/1793576
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 23
  • ???jsp.display-item.citation.isi??? 14
social impact