The problem of secure data processing by means of a neu- ral network (NN) is addressed. Secure processing refers to the possibility that the NN owner does not get any knowl- edge about the processed data since they are provided to him in encrypted format. At the same time, the NN it- self is protected, given that its owner may not be willing to disclose the knowledge embedded within it. Two di®erent levels of protection are considered: according to the ¯rst one only the NN weights are protected, whereas the second level also permits to protect the node activation functions. An e±cient way of implementing the proposed protocol by means of some recently proposed multi-party computation techniques is described.
A Privacy Preserving Protocol for Neural-Network-Based Computation / M. Barni; C. Orlandi; A. Piva. - STAMPA. - (2006), pp. 146-151. (Intervento presentato al convegno VIII ACM Multimedia and Security Workshop 2006 tenutosi a Geneva, Switzerland nel September 26-27, 2006).
A Privacy Preserving Protocol for Neural-Network-Based Computation
PIVA, ALESSANDRO
2006
Abstract
The problem of secure data processing by means of a neu- ral network (NN) is addressed. Secure processing refers to the possibility that the NN owner does not get any knowl- edge about the processed data since they are provided to him in encrypted format. At the same time, the NN it- self is protected, given that its owner may not be willing to disclose the knowledge embedded within it. Two di®erent levels of protection are considered: according to the ¯rst one only the NN weights are protected, whereas the second level also permits to protect the node activation functions. An e±cient way of implementing the proposed protocol by means of some recently proposed multi-party computation techniques is described.
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
