Adversarial attacks on medical machine learning
2019/03/21 by Samuel G. Finlayson, John D. Bowers, Joichi Ito +4 · 1,043 citations
Computer Science · Medicine · #Adversarial Robustness in Machine Learning #Adversarial machine learning #Adversarial system #Artificial Intelligence in Healthcare and Education #Artificial intelligence #Computer science #Computer security #Data science #Ethics in Clinical Research #Internet privacy #Machine learning
paper · open access · doi:10.1126/science.aaw4399
published in Science 363(6433), 1287-1289 (American Association for the Advancement of Science)
openalex publication_date 2019/03/21 · openalex created_date 2019/04/01 · openalex updated_date 2026/08/01
Abstract
Emerging vulnerabilities demand new conversations
Cited by
- Anwendungen, Herausforderungen und ein vertrauenswürdiger Umgang mit künstlicher Intelligenz im Bereich Public Health
- Robust convolutional neural networks against adversarial attacks on medical images
- Generating Synthetic Data for Medical Imaging
- SafeMed-R1: Adversarial Reinforcement Learning for Generalizable and Robust Medical Reasoning in Vision-Language Models
- Foundation Models in Biomedical Imaging: Turning Hype into Reality
- A Practical Framework for Evaluating Medical AI Security: Reproducible Assessment of Jailbreaking and Privacy Vulnerabilities Across Clinical Specialties
- Worst-case generation via minimax optimization in Wasserstein space
- Many-to-One Adversarial Consensus: Exposing Multi-Agent Collusion Risks in AI-Based Healthcare
- The Double-Edged Nature of the Rashomon Set for Trustworthy Machine Learning
- Deep Learning in Computer-Aided Diagnosis and Treatment of Tumors: A Survey
- SkinGPT-R1: Adapter-Only Dual Distillation for Efficient Dermatology Reasoning
- Can Large Language Models Function as Qualified Pediatricians? A Systematic Evaluation in Real-World Clinical Contexts
- Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks
- Filtered-ViT: A Robust Defense Against Multiple Adversarial Patch Attacks
- Clean-Label Backdoor Attacks on Video Recognition Models
- An Explainable Artificial Intelligence Approach Using Graph Learning to Predict Intensive Care Unit Length of Stay
- GNNGuard: Defending Graph Neural Networks against Adversarial Attacks
- Adversarial Visual Robustness by Causal Intervention
- Local Competition and Uncertainty for Adversarial Robustness in Deep Learning
- Development and Validation of a Deep Learning Model to Reduce the Interference of Rectal Artifacts in MRI-based Prostate Cancer Diagnosis
- Adversarially-Aware Architecture Design for Robust Medical AI Systems
- Constrained Adversarial Perturbation
- Are Labels Required for Improving Adversarial Robustness?
- A tailor-made 3-dimensional directional Haar semi-tight framelet for pMRI reconstruction
- Measurements, Algorithms, and Presentations of Reality: Framing Interactions with AI-Enabled Decision Support
- Recent Advances in Fibrosis and Scar Segmentation from Cardiac MRI: A State-of-the-Art Review and Future Perspectives
- Adversarial Heart Attack: Neural Networks Fooled to Segment Heart Symbols in Chest X-Ray Images
- Hallucinations in medical devices
- Cyber Risks to Next-Gen Brain-Computer Interfaces: Analysis and Recommendations
- Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation
- Stabilizing Deep Tomographic Reconstruction
- Robust, Deep, and Reinforcement Learning for Management of Communication and Power Networks
- Improved Adversarial Robustness via Logit Regularization Methods
- AN-GCN: An Anonymous Graph Convolutional Network Defense Against Edge-Perturbing Attack
- Training or Architecture? How to Incorporate Invariance in Neural Networks
- Security in Brain-Computer Interfaces: State-of-the-art, opportunities, and future challenges
- Artificial Intelligence and Corruption: Opportunities and Challenges in the Health Sector
- Improved Detection of Adversarial Images Using Deep Neural Networks
- Fuzzy Unique Image Transformation: Defense Against Adversarial Attacks On Deep COVID-19 Models
- Adaptive Diffusion Denoised Smoothing : Certified Robustness via Randomized Smoothing with Differentially Private Guided Denoising Diffusion
- The K-Space Signature: Frequency-Domain Representation Learning for Medical Deepfake Detection
- Dual Head Adversarial Training
- Are Vision Transformer Representations Semantically Meaningful? A Case Study in Medical Imaging
- Power and reproducibility in the external validation of brain-phenotype predictions
- From Shallow to Deep Interactions Between Knowledge Representation, Reasoning and Machine Learning (Kay R. Amel group)
- VSF-Med:A Vulnerability Scoring Framework for Medical Vision-Language Models
- An Attack Method for Medical Insurance Claim Fraud Detection based on Generative Adversarial Network
- AI Safety vs. AI Security: Demystifying the Distinction and Boundaries
- Systems-Theoretic and Data-Driven Security Analysis in ML-enabled Medical Devices
- Position: Certified Robustness Does Not (Yet) Imply Model Security
- FUTURE-AI: international consensus guideline for trustworthy and deployable artificial intelligence in healthcare
- Statistically Valid Post-Deployment Monitoring Should Be Standard for AI-Based Digital Health
- Machine learning and behavioral economics for personalized choice architecture
- Sample-Specific Noise Injection For Diffusion-Based Adversarial Purification
- Assured Autonomy with Neuro-Symbolic Perception
- Catastrophic Overfitting, Entropy Gap and Participation Ratio: A Noiseless lp Norm Solution for Fast Adversarial Training
- A Decade of Healthcare Cyber Threats: Empirical Analysis, Evidence-Based Prioritisation, and AI Threat Model
- Integration of TinyML and LargeML: A Survey of 6G and Beyond
- Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI Extension
- Explainability Matters: Backdoor Attacks on Medical Imaging
- Towards a safe and efficient clinical implementation of machine learning in radiation oncology by exploring model interpretability, explainability and data-model dependency
- What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data
- Local Competition and Stochasticity for Adversarial Robustness in Deep Learning
- ATHENA: A Framework based on Diverse Weak Defenses for Building Adversarial Defense
- Adversarial Interaction Attack: Fooling AI to Misinterpret Human Intentions
- Federated learning, ethics, and the double black box problem in medical AI
- Noninterpretive Uses of Artificial Intelligence in Radiology
- MUTEN: Boosting Gradient-Based Adversarial Attacks via Mutant-Based Ensembles
- Why deep-learning AIs are so easy to fool
- Distributionally Robust Multi-Output Regression Ranking
- Quantifying the Uncertainty of Precision Estimates for Rule based Text Classifiers
- Deep Positive-Negative Prototypes for Adversarially Robust Discriminative Prototypical Learning
- AI in Health: State of the Art, Challenges, and Future Directions. [europepmc]
- Key challenges for delivering clinical impact with artificial intelligence. [europepmc]
- Introducing Artificial Intelligence Training in Medical Education. [europepmc]
- An introduction to deep learning in medical physics: advantages, potential, and challenges. [europepmc]
- Deep Learning for Cardiac Image Segmentation: A Review. [europepmc]
- Machine intelligence in healthcare-perspectives on trustworthiness, explainability, usability, and transparency. [europepmc]
- Artificial Intelligence and Orthopaedics: An Introduction for Clinicians. [europepmc]
- Current Challenges and Barriers to Real-World Artificial Intelligence Adoption for the Healthcare System, Provider, and the Patient. [europepmc]
- Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI Extension. [europepmc]
- Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension. [europepmc]
- Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension. [europepmc]
- Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI Extension. [europepmc]
- Deep neural network models for computational histopathology: A survey. [europepmc]
- Regulatory Frameworks for Development and Evaluation of Artificial Intelligence-Based Diagnostic Imaging Algorithms: Summary and Recommendations. [europepmc]
- Identifying Ethical Considerations for Machine Learning Healthcare Applications. [europepmc]
- Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension. [europepmc]
- Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension. [europepmc]
- Second opinion needed: communicating uncertainty in medical machine learning. [europepmc]
- Human-interpretable image features derived from densely mapped cancer pathology slides predict diverse molecular phenotypes. [europepmc]
- Swarm Learning for decentralized and confidential clinical machine learning. [europepmc]
- Synthetic data in machine learning for medicine and healthcare. [europepmc]
- Ethics and governance of trustworthy medical artificial intelligence. [europepmc]
- Large language model (ChatGPT) as a support tool for breast tumor board. [europepmc]
- Leveraging Generative AI and Large Language Models: A Comprehensive Roadmap for Healthcare Integration. [europepmc]
- FUTURE-AI: international consensus guideline for trustworthy and deployable artificial intelligence in healthcare. [europepmc]
Related