In this paper, the security of the compressed sensing (CS) framework as a form of data confidentiality is analyzed. Two important properties of one-time random linear measurements acquired using a Gaussian i.i.d. matrix are outlined: i) the measurements reveal only the energy of the sensed signal; ii) only the energy of the measurements leaks information about the signal. An important consequence of the above facts is that CS provides information theoretic secrecy in a particular setting. Namely, a simple strategy based on the normalization of Gaussian measurements achieves, at least in theory, perfect secrecy, enabling the use of CS as an additional security layer in privacy preserving applications. In the generic setting in which CS does not provide information theoretic secrecy, two alternative security notions linked to the difficulty of estimating the energy of the signal and distinguishing equal-energy signals are introduced. Useful bounds on the mean square error of any possible estimator and the probability of error of any possible detector are provided and compared to simulations. The results indicate that CS is in general not secure according to cryptographic standards, but may provide a useful built-in data obfuscation layer.

Analysis of One-Time Random Projections for Privacy Preserving Compressed Sensing / Bianchi, Tiziano; Bioglio, Valerio; Magli, Enrico. - In: IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY. - ISSN 1556-6013. - STAMPA. - 11:2(2016), pp. 313-327. [10.1109/TIFS.2015.2493982]

Analysis of One-Time Random Projections for Privacy Preserving Compressed Sensing

BIANCHI, TIZIANO;BIOGLIO, VALERIO;MAGLI, ENRICO
2016

Abstract

In this paper, the security of the compressed sensing (CS) framework as a form of data confidentiality is analyzed. Two important properties of one-time random linear measurements acquired using a Gaussian i.i.d. matrix are outlined: i) the measurements reveal only the energy of the sensed signal; ii) only the energy of the measurements leaks information about the signal. An important consequence of the above facts is that CS provides information theoretic secrecy in a particular setting. Namely, a simple strategy based on the normalization of Gaussian measurements achieves, at least in theory, perfect secrecy, enabling the use of CS as an additional security layer in privacy preserving applications. In the generic setting in which CS does not provide information theoretic secrecy, two alternative security notions linked to the difficulty of estimating the energy of the signal and distinguishing equal-energy signals are introduced. Useful bounds on the mean square error of any possible estimator and the probability of error of any possible detector are provided and compared to simulations. The results indicate that CS is in general not secure according to cryptographic standards, but may provide a useful built-in data obfuscation layer.
File in questo prodotto:
File Dimensione Formato  
bianTIFS15.pdf

non disponibili

Descrizione: Articolo versione publisher
Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 1.99 MB
Formato Adobe PDF
1.99 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
bianTIFS15_OA.pdf

accesso aperto

Descrizione: Articolo versione open access
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 2.7 MB
Formato Adobe PDF
2.7 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

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/11583/2627688
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo