Hacking smart machines with smarter ones: How to extract meaningful data from machine learning classifiers
| Autor: | Angelo Spognardi, Domenico Vitali, Giuseppe Ateniese, Luigi V. Mancini, Giovanni Felici, Antonio Villani |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2015 |
| Předmět: |
FOS: Computer and information sciences
Risk Computer Science - Cryptography and Security Information leakages Computer science Vendor Computer Networks and Communications Machine Learning (stat.ML) Intellectual property Machine learning computer.software_genre Attacks methodology Intellectual property rights ML Security Trade secrets Unauthorised access Electrical and Electronic Engineering Safety Risk Reliability and Quality Machine Learning (cs.LG) Statistics - Machine Learning Hacker Focus (computing) business.industry Computer Science - Learning Reliability and Quality Information leakage Artificial intelligence Safety business computer Cryptography and Security (cs.CR) |
| Zdroj: | International journal of security and networks info:cnr-pdr/source/autori:Ateniese G.; Mancini L.V.; Spognardi A.; Villani A.; Vitali D.; Felici G./titolo:Hacking smart machines with smarter ones: How to extract meaningful data from machine learning classifiers/doi:10.1504%2FIJSN.2015.071829/rivista:International journal of security and networks (Print)/anno:2015/pagina_da:137/pagina_a:150/intervallo_pagine:137–150/volume:10 |
| Popis: | Machine Learning (ML) algorithms are used to train computers to perform a variety of complex tasks and improve with experience. Computers learn how to recognize patterns, make unintended decisions, or react to a dynamic environment. Certain trained machines may be more effective than others because they are based on more suitable ML algorithms or because they were trained through 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. While much research has been performed about the privacy of the elements of training sets, 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. This kind of 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|