Hacking Smart Machines with Smarter Ones: How to Extract Meaningful Data from Machine Learning Classifiers

TL;DR

This paper demonstrates how to extract sensitive information from machine learning classifiers by building a meta-classifier that can infer details about the training data, highlighting potential privacy and intellectual property risks.

Contribution

It introduces a novel meta-classifier approach to hack ML classifiers and reveal information about their training sets, exposing privacy vulnerabilities.

Findings

Meta-classifier successfully infers training data details

Information leakage can compromise trade secrets

Potential for misuse in competitive scenarios

Abstract

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.