mlsanityData to 7 Oct 2026

The Security of Deep Learning Defences for Medical Imaging

arXiv 2201.08661 ↗First posted 21 Jan 2022cs.CR cs.LG eess.IVcited by 4

Not on the map. Why?

Abstract (arXiv)

Deep learning has shown great promise in the domain of medical image analysis. Medical professionals and healthcare providers have been adopting the technology to speed up and enhance their work. These systems use deep neural networks (DNN) which are vulnerable to adversarial samples; images with imperceivable changes that can alter the model's prediction. Researchers have proposed defences which either make a DNN more robust or detect the adversarial samples before they do harm. However, none of these works consider an informed attacker which can adapt to the defence mechanism. We show that an informed attacker can evade five of the current state of the art defences while successfully fooling the victim's deep learning model, rendering these defences useless. We then suggest better alternatives for securing healthcare DNNs from such attacks: (1) harden the system's security and (2) use digital signatures.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 31 of its 59 references that are in the map. First posted on arXiv 21 Jan 2022.

Builds on

31 of 59 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  7. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  8. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,182
  9. 2016Adversarial Machine Learning at Scalecited by 934
  10. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  11. 2016Universal adversarial perturbationscited by 774
  12. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
19 more
  1. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  2. 2017Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)cited by 549
  3. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
  4. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  5. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  6. 2016Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challengecited by 198
  7. 2019Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systemscited by 151
  8. 2020Adversarial Camouflage: Hiding Physical-World Attacks with Natural Stylescited by 126
  9. 2020The Translucent Patch: A Physical and Universal Attack on Object Detectorscited by 62
  10. 2018Adversarial Attacks Against Medical Deep Learning Systemscited by 61
  11. 2018Stealing Neural Networks via Timing Side Channelscited by 42
  12. 2021The Dimpled Manifold Model of Adversarial Examples in Machine Learningcited by 41
  13. 2017Adversarial Example Defenses: Ensembles of Weak Defenses are not Strongcited by 32
  14. 2019CT-GAN: Malicious Tampering of 3D Medical Imagery using Deep Learningcited by 31
  15. 2020Stealing Deep Reinforcement Learning Models for Fun and Profitcited by 24
  16. 2019A Kernelized Manifold Mapping to Diminish the Effect of Adversarial Perturbationscited by 11
  17. 2020Defending against adversarial attacks on medical imaging AI system, classification or detection?cited by 6
  18. 2018Detecting Adversarial Perturbations Through Spatial Behavior in Activation Spacescited by 4
  19. 2019Improved ICH classification using task-dependent learningcited by 1

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1; 2024: 1.

4 papers.

  1. 2023Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and Challengescited by 16
  2. 2024A Survey on Offensive AI Within Cybersecuritycited by 3
  3. 2022Data Stealing Attack on Medical Images: Is it Safe to Export Networks from Data Lakes?cited by 2
  4. 2022Transferability Ranking of Adversarial Examplescited by 1