Adversarial attacks on medical machine learning

Finlayson, Samuel G.; Bowers, John; Ito, Joichi; Zittrain, Jonathan; Beam, Andrew L.; Kohane, Isaac S.

doi:10.1126/science.aaw4399

Cited by 760 publications

(513 citation statements)

References 8 publications

Supporting

Mentioning

503

Contrasting

Unclassified

Order By: Relevance

“…These attacks can also happen in medical scenarios, e.g. a DL-based system may make a wrong diagnosis given an image with adversarial noise or even just small rotation, as demonstrated in a very recent paper (Finlayson et al, 2019). Although there is no denying that deep learning has become a very powerful tool for image analysis, building resilient algorithms robust to potential attacks remains an unsolved problem.…”

Section: Lack Of Model Interpretabilitymentioning

confidence: 99%

Deep Learning for Cardiac Image Segmentation: A Review

Chen

Qiu

et al. 2020

Front. Cardiovasc. Med.

607

383

View full text Add to dashboard Cite

Deep learning has become the most widely used approach for cardiac image segmentation in recent years. In this paper, we provide a review of over 100 cardiac image segmentation papers using deep learning, which covers common imaging modalities including magnetic resonance imaging (MRI), computed tomography (CT), and ultrasound (US) and major anatomical structures of interest (ventricles, atria and vessels). In addition, a summary of publicly available cardiac image datasets and code repositories are included to provide a base for encouraging reproducible research. Finally, we discuss the challenges and limitations with current deep learning-based approaches (scarcity of labels, model generalizability across different domains, interpretability) and suggest potential directions for future research.

show abstract

Section: Lack Of Model Interpretabilitymentioning

confidence: 99%

Deep Learning for Cardiac Image Segmentation: A Review

Chen

Qiu

et al. 2020

Front. Cardiovasc. Med.

607

383

View full text Add to dashboard Cite

show abstract

“…AEs bring a great threat to the security-critical AI applications such as face payment [64], medical systems [65] and autonomous vehicles [66], [67] based on image recognition in deep learning. Vulnerability to AEs is not unique to deep learning.…”

Section: Defenses Against Adversarial Examplesmentioning

confidence: 99%

Adversarial Examples: Opportunities and Challenges

Zhang

2019

IEEE Trans. Neural Netw. Learning Syst.

135

View full text Add to dashboard Cite

Deep neural networks (DNNs) have shown huge superiority over humans in image recognition, speech processing, autonomous vehicles and medical diagnosis. However, recent studies indicate that DNNs are vulnerable to adversarial examples (AEs) which are designed by attackers to fool deep learning models. Different from real examples, AEs can mislead the model to predict incorrect outputs while hardly be distinguished by human eyes, therefore threaten security-critical deep-learning applications. In recent years, the generation and defense of AEs have become a research hotspot in the field of artificial intelligence (AI) security. This article reviews the latest research progress of AEs. First, we introduce the concept, cause, characteristics and evaluation metrics of AEs, then give a survey on the state-of-the-art AE generation methods with the discussion of advantages and disadvantages. After that, we review the existing defenses and discuss their limitations. Finally, future research opportunities and challenges on AEs are prospected.

show abstract

“…By diagonalizing the data matrix and using similar arguments in Appendix A, (16) can be further simplified as…”

Section: B Case With K < Rank(x)mentioning

confidence: 99%

On the Adversarial Robustness of Subspace Learning

Lai

Cui

2020

IEEE Trans. Signal Process.

View full text Add to dashboard Cite

In this paper, we study the adversarial robustness of subspace learning problems. Different from the assumptions made in existing work on robust subspace learning where data samples are contaminated by gross sparse outliers or small dense noises, we consider a more powerful adversary who can first observe the data matrix and then intentionally modify the whole data matrix. We first characterize the optimal rank-one attack strategy that maximizes the subspace distance between the subspace learned from the original data matrix and that learned from the modified data matrix. We then generalize the study to the scenario without the rank constraint and characterize the corresponding optimal attack strategy. Our analysis shows that the optimal strategies depend on the singular values of the original data matrix and the adversary's energy budget. Finally, we provide numerical experiments and practical applications to demonstrate the efficiency of the attack strategies.

show abstract

Adversarial attacks on medical machine learning

Abstract: Emerging vulnerabilities demand new conversations

Cited by 760 publications

References 8 publications

Deep Learning for Cardiac Image Segmentation: A Review

Deep Learning for Cardiac Image Segmentation: A Review

Adversarial Examples: Opportunities and Challenges

On the Adversarial Robustness of Subspace Learning

Contact Info

Product

Resources

About