Machine-learning (ML) enables computers to learn how to recognise patterns, make unintended decisions, or react to a dynamic environment. The effectiveness of trained machines varies because of more suitable ML algorithms or because superior training sets. Although ML algorithms are known and publicly released, training sets may not be reasonably ascertainable and, indeed, may be guarded as trade secrets. In this paper we focus our attention on ML classifiers and on the statistical information that can be unconsciously or maliciously revealed from them. We show that it is possible to infer unexpected but useful information from ML classifiers. In particular, we build a novel meta-classifier and train it to hack other classifiers, obtaining meaningful information about their training sets. Such information leakage can be exploited, for example, by a vendor to build more effective classifiers or to simply acquire trade secrets from a competitor's apparatus, potentially violating its intellectual property rights.

Hacking smart machines with smarter ones: How to extract meaningful data from machine learning classifiers / Ateniese, Giuseppe; Mancini, Luigi Vincenzo; Spognardi, Angelo; Villani, Antonio; Vitali, Domenico; Felici, Giovanni. - In: INTERNATIONAL JOURNAL OF SECURITY AND NETWORKS. - ISSN 1747-8405. - STAMPA. - 10:3(2015), pp. 137-150. [10.1504/IJSN.2015.071829]

Hacking smart machines with smarter ones: How to extract meaningful data from machine learning classifiers

ATENIESE, GIUSEPPE;MANCINI, Luigi Vincenzo;SPOGNARDI, Angelo;VILLANI, Antonio;VITALI, Domenico;
2015

Abstract

Machine-learning (ML) enables computers to learn how to recognise patterns, make unintended decisions, or react to a dynamic environment. The effectiveness of trained machines varies because of more suitable ML algorithms or because superior training sets. Although ML algorithms are known and publicly released, training sets may not be reasonably ascertainable and, indeed, may be guarded as trade secrets. In this paper we focus our attention on ML classifiers and on the statistical information that can be unconsciously or maliciously revealed from them. We show that it is possible to infer unexpected but useful information from ML classifiers. In particular, we build a novel meta-classifier and train it to hack other classifiers, obtaining meaningful information about their training sets. Such information leakage can be exploited, for example, by a vendor to build more effective classifiers or to simply acquire trade secrets from a competitor's apparatus, potentially violating its intellectual property rights.
2015
Attacks methodology; Information leakages; Intellectual property rights; Machine learning; ML; Security; Trade secrets; Unauthorised access; Electrical and Electronic Engineering; Computer Networks and Communications; Safety, Risk, Reliability and Quality
01 Pubblicazione su rivista::01a Articolo in rivista
Hacking smart machines with smarter ones: How to extract meaningful data from machine learning classifiers / Ateniese, Giuseppe; Mancini, Luigi Vincenzo; Spognardi, Angelo; Villani, Antonio; Vitali, Domenico; Felici, Giovanni. - In: INTERNATIONAL JOURNAL OF SECURITY AND NETWORKS. - ISSN 1747-8405. - STAMPA. - 10:3(2015), pp. 137-150. [10.1504/IJSN.2015.071829]
File allegati a questo prodotto
Non ci sono file associati a questo prodotto.

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/11573/878035
 Attenzione

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

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 267
  • ???jsp.display-item.citation.isi??? ND
social impact