Does Proprietary Software Still Offer Protection of Intellectual Property in the Age of Machine Learning? -- A Case Study using Dual Energy CT Data

TL;DR

This study examines whether proprietary binary medical image processing software can be reverse-engineered using machine learning, demonstrating high-accuracy approximations of complex algorithms from minimal training data.

Contribution

It provides empirical evidence that proprietary algorithms in medical imaging are vulnerable to machine learning-based reverse engineering, challenging assumptions about intellectual property protection.

Findings

Mono-energetic image computation can be approximated with high accuracy.

Iodine map algorithms are also highly susceptible to reverse engineering.

High structural similarity (>0.98) achieved with minimal training data.

Abstract

In the domain of medical image processing, medical device manufacturers protect their intellectual property in many cases by shipping only compiled software, i.e. binary code which can be executed but is difficult to be understood by a potential attacker. In this paper, we investigate how well this procedure is able to protect image processing algorithms. In particular, we investigate whether the computation of mono-energetic images and iodine maps from dual energy CT data can be reverse-engineered by machine learning methods. Our results indicate that both can be approximated using only one single slice image as training data at a very high accuracy with structural similarity greater than 0.98 in all investigated cases.