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.
Blog Post:
https://towardsdatascience.com/how-we-hacked-commercial-image-processing-software-using-machine-learning-38e9bbea3bb9
Paper:
https://link.springer.com/chapter/10.1007/978-3-658-36932-3_70
CONRAD:
https://www5.cs.fau.de/conrad/
PYCONRAD:
https://git5.cs.fau.de/PyConrad/pyCONRAD
(try pip install pyconrad)
For reminders to watch the new video follow on Twitter https://twitter.com/maier_ak or LinkedIn https://www.linkedin.com/in/andreas-maier-a6870b1a6/.
Interested in joining our network? Get reminders for talks, videos and job offers related to machine learning here: https://lme.tf.fau.de/lab/join-the-pattern-recognition-lab/
Music References:
Intro: Tri-Tachyon - The Spellbreaker https://freemusicarchive.org/music/Tri-Tachyon/The_Spellbreaker_EP/The_Spellbreaker
Background Music: Loyalty Freak Music - Maxi Metal https://freemusicarchive.org/music/Loyalty_Freak_Music/HYPER_METAL_/Loyalty_Freak_Music_-_HYPER_METAL__-_02_MAXI_METAL
Outro: Psalters - We are all lepers here https://freemusicarchive.org/music/Psalters/us_vs_us/02_We_Are_All_Lepers_Here_vbr