Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
134 tokens/sec
GPT-4o
9 tokens/sec
Gemini 2.5 Pro Pro
47 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

The Art of the Steal: Purloining Deep Learning Models Developed for an Ultrasound Scanner to a Competitor Machine (2407.03512v1)

Published 3 Jul 2024 in eess.IV

Abstract: A transfer function approach has recently proven effective for calibrating deep learning (DL) algorithms in quantitative ultrasound (QUS), addressing data shifts at both the acquisition and machine levels. Expanding on this approach, we develop a strategy to 'steal' the functionality of a DL model from one ultrasound machine and implement it on another, in the context of QUS. This demonstrates the ease with which the functionality of a DL model can be transferred between machines, highlighting the security risks associated with deploying such models in a commercial scanner for clinical use. The proposed method is a black-box unsupervised domain adaptation technique that integrates the transfer function approach with an iterative schema. It does not utilize any information related to model internals of the victim machine but it solely relies on the availability of input-output interface. Additionally, we assume the availability of unlabelled data from the testing machine, i.e., the perpetrator machine. This scenario could become commonplace as companies begin deploying their DL functionalities for clinical use. Competing companies might acquire the victim machine and, through the input-output interface, replicate the functionality onto their own machines. In the experiments, we used a SonixOne and a Verasonics machine. The victim model was trained on SonixOne data, and its functionality was then transferred to the Verasonics machine. The proposed method successfully transferred the functionality to the Verasonics machine, achieving a remarkable 98\% classification accuracy in a binary decision task. This study underscores the need to establish security measures prior to deploying DL models in clinical settings.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (10)
  1. T. Nguyen and M. Oelze, “Reference free quantitative ultrasound classification of fatty liver,” in 2019 IEEE International Ultrasonics Symposium (IUS).   IEEE, 2019, pp. 2424–2427.
  2. H. Taleghamar, S. A. Jalalifar, G. J. Czarnota, and A. Sadeghi-Naini, “Deep learning of quantitative ultrasound multi-parametric images at pre-treatment to predict breast cancer response to chemotherapy,” Scientific reports, vol. 12, no. 1, p. 2244, 2022.
  3. S. K. Jeon, J. M. Lee, I. Joo, J. H. Yoon, and G. Lee, “Two-dimensional convolutional neural network using quantitative us for noninvasive assessment of hepatic steatosis in nafld,” Radiology, vol. 307, no. 1, p. e221510, 2023.
  4. U. Soylu and M. L. Oelze, “Calibrating data mismatches in deep learning-based quantitative ultrasound using setting transfer functions,” IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 2023.
  5. U. Soylu and M. L. Oelze, “A data-efficient deep learning strategy for tissue characterization via quantitative ultrasound: Zone training,” IEEE transactions on ultrasonics, ferroelectrics, and frequency control, 2023.
  6. U. Soylu and M. L. Oelze, “Machine-to-machine transfer function in deep learning-based quantitative ultrasound,” arXiv preprint arXiv:2311.16028, 2023.
  7. J. Liang, R. He, and T. Tan, “A comprehensive survey on test-time adaptation under distribution shifts,” arXiv preprint arXiv:2303.15361, 2023.
  8. H. Zhang, Y. Zhang, K. Jia, and L. Zhang, “Unsupervised domain adaptation of black-box source models,” arXiv preprint arXiv:2101.02839, 2021.
  9. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014.
  10. V. Chandrasekaran, K. Chaudhuri, I. Giacomelli, S. Jha, and S. Yan, “Exploring connections between active learning and model extraction,” in 29th USENIX Security Symposium (USENIX Security 20).   USENIX Association, Aug. 2020. [Online]. Available: https://www.usenix.org/conference/usenixsecurity20/presentation/chandrasekaran pp. 1309–1326.

Summary

We haven't generated a summary for this paper yet.

X Twitter Logo Streamline Icon: https://streamlinehq.com