mlsanityData to 7 Oct 2026

SoK: Security and Privacy Risks of Healthcare AI

arXiv 2409.07415 ↗First posted 11 Sep 2024cs.CR cs.AI cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

The integration of artificial intelligence (AI) and machine learning (ML) into healthcare systems holds great promise for enhancing patient care and care delivery efficiency; however, it also exposes sensitive data and system integrity to potential cyberattacks. Current security and privacy (S&P) research on healthcare AI is highly unbalanced in terms of healthcare deployment scenarios and threat models, and has a disconnected focus with the biomedical research community. This hinders a comprehensive understanding of the risks that healthcare AI entails. To address this gap, this paper takes a thorough examination of existing healthcare AI S&P research, providing a unified framework that allows the identification of under-explored areas. Our survey presents a systematic overview of healthcare AI attacks and defenses, and points out challenges and research opportunities for each AI-driven healthcare application domain. Through our experimental analysis of different threat models and feasibility studies on under-explored adversarial attacks, we provide compelling insights into the pressing need for cybersecurity research in the rapidly evolving field of healthcare AI.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 89 of its 206 references that are in the map. First posted on arXiv 11 Sep 2024.

Builds on

89 of 206 references.

References · 89

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  5. 2023BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairscited by 506
  6. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  7. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 328
  8. 2017Multitask learning and benchmarking with clinical time series datacited by 287
  9. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 273
  10. 2017Molecular De Novo Design through Deep Reinforcement Learningcited by 264
  11. 2021Enhanced Membership Inference Attacks against Machine Learning Modelscited by 237
  12. 2018Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learningcited by 219
38 more
  1. 2021Evaluating Deep Neural Networks Trained on Clinical Images in Dermatology with the Fitzpatrick 17k Datasetcited by 184
  2. 2017Learning to Plan Chemical Synthesescited by 175
  3. 2022Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attackscited by 168
  4. 2020Membership Leakage in Label-Only Exposurescited by 156
  5. 2019Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systemscited by 151
  6. 2019Privacy Risks of Securing Machine Learning Models against Adversarial Examplescited by 136
  7. 2019Sign-OPT: A Query-Efficient Hard-label Adversarial Attackcited by 118
  8. 2021Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?cited by 91
  9. 2021ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Modelscited by 79
  10. 2018Technical Report: When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attackscited by 78
  11. 2018Adversarial Attacks Against Medical Deep Learning Systemscited by 61
  12. 2021FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysiscited by 60
  13. 2020Data Poisoning Attacks on Federated Machine Learningcited by 58
  14. 2023Label-Free Liver Tumor Segmentationcited by 56
  15. 2021Membership Inference Attacks Against Recommender Systemscited by 52
  16. 2020Can We Use Split Learning on 1D CNN Models for Privacy Preserving Training?cited by 50
  17. 2021Membership Inference Attack Susceptibility of Clinical Language Modelscited by 50
  18. 2022A Multimodal Transformer: Fusing Clinical Notes with Structured EHR Data for Interpretable In-Hospital Mortality Predictioncited by 48
  19. 2022SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learningcited by 47
  20. 2024AI auditing: The Broken Bus on the Road to AI Accountabilitycited by 42
  21. 2020Adversarial Attack Vulnerability of Medical Image Analysis Systems: Unexplored Factorscited by 39
  22. 2019CT-GAN: Malicious Tampering of 3D Medical Imagery using Deep Learningcited by 31
  23. 2022M^4I: Multi-modal Models Membership Inferencecited by 30
  24. 2019Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentationcited by 26
  25. 2022A Unified Review of Deep Learning for Automated Medical Codingcited by 26
  26. 2020Miss the Point: Targeted Adversarial Attack on Multiple Landmark Detectioncited by 21
  27. 2022SoK: Explainable Machine Learning for Computer Security Applicationscited by 20
  28. 2021Membership Inference Attacks on Deep Regression Models for Neuroimagingcited by 19
  29. 2023Explainable Brain Age Prediction using coVariance Neural Networkscited by 19
  30. 2021A Framework for Fairness: A Systematic Review of Existing Fair AI Solutionscited by 18
  31. 2023Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and Challengescited by 16
  32. 2024Stable Diffusion Segmentation for Biomedical Images with Single-step Reverse Processcited by 16
  33. 2018Identify Susceptible Locations in Medical Records via Adversarial Attacks on Deep Predictive Modelscited by 15
  34. 2024Safeguarding Medical Image Segmentation Datasets against Unauthorized Training via Contour- and Texture-Aware Perturbationscited by 15
  35. 2017Simultaneous Recognition and Pose Estimation of Instruments in Minimally Invasive Surgerycited by 14
  36. 2023SoK: Pragmatic Assessment of Machine Learning for Network Intrusion Detectioncited by 13
  37. 2020Adversarial Attacks to Machine Learning-Based Smart Healthcare Systemscited by 12
  38. 2020Advancing diagnostic performance and clinical usability of neural networks via adversarial training and dual batch normalizationcited by 12

50 most cited of 89 All 89 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 1.

2 papers.

  1. 2024Sequential LLM Framework for Fashion Recommendationcited by 6
  2. 2026Backdoor Learning in Language Models and Vision-Language Modelscited by 0