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

by   Giuseppe Ateniese, et al.

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.


page 1

page 2

page 3

page 4


Inferring Class Label Distribution of Training Data from Classifiers: An Accuracy-Augmented Meta-Classifier Attack

Property inference attacks against machine learning (ML) models aim to i...

Over-the-Air Membership Inference Attacks as Privacy Threats for Deep Learning-based Wireless Signal Classifiers

This paper presents how to leak private information from a wireless sign...

Supervised Machine Learning with Plausible Deniability

We study the question of how well machine learning (ML) models trained o...

When Homomorphic Cryptosystem Meets Differential Privacy: Training Machine Learning Classifier with Privacy Protection

Machine learning (ML) classifiers are invaluable building blocks that ha...

Decoding machine learning benchmarks

Despite the availability of benchmark machine learning (ML) repositories...

Injective Domain Knowledge in Neural Networks for Transprecision Computing

Machine Learning (ML) models are very effective in many learning tasks, ...

Data Acquisition for Improving Machine Learning Models

The vast advances in Machine Learning over the last ten years have been ...

Please sign up or login with your details

Forgot password? Click here to reset