mlsanityData to 7 Oct 2026

Out of Distribution Detection and Adversarial Attacks on Deep Neural Networks for Robust Medical Image Analysis

arXiv 2107.04882 ↗First posted 10 Jul 2021cs.CV cs.LG eess.IVcited by 10

Not on the map. Why?

Abstract (arXiv)

Deep learning models have become a popular choice for medical image analysis. However, the poor generalization performance of deep learning models limits them from being deployed in the real world as robustness is critical for medical applications. For instance, the state-of-the-art Convolutional Neural Networks (CNNs) fail to detect adversarial samples or samples drawn statistically far away from the training distribution. In this work, we experimentally evaluate the robustness of a Mahalanobis distance-based confidence score, a simple yet effective method for detecting abnormal input samples, in classifying malaria parasitized cells and uninfected cells. Results indicated that the Mahalanobis confidence score detector exhibits improved performance and robustness of deep learning models, and achieves stateof-the-art performance on both out-of-distribution (OOD) and adversarial samples.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 13 of its 32 references that are in the map. First posted on arXiv 10 Jul 2021.

Builds on

13 of 32 references.

References · 13

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  3. 2016Adversarial examples in the physical worldcited by 1,762
  4. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  5. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  6. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  7. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  8. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 280
  9. 2016Robustness of classifiers: from adversarial to random noisecited by 87
  10. 2020Robust Out-of-distribution Detection for Neural Networkscited by 57
  11. 2020Out-of-Distribution Detection for Automotive Perceptioncited by 37
  12. 2020Why is the Mahalanobis Distance Effective for Anomaly Detection?cited by 28
1 more
  1. 2020Objective Evaluation of Deep Uncertainty Predictions for COVID-19 Detectioncited by 20

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 5; 2023: 3; 2024: 1.

10 papers.

  1. 2023Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and Challengescited by 16
  2. 2023On the use of Mahalanobis distance for out-of-distribution detection with neural networks for medical imagingcited by 15
  3. 2022CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learningcited by 11
  4. 2022Topological Structure Learning for Weakly-Supervised Out-of-Distribution Detectioncited by 4
  5. 2022AutoMO-Mixer: An automated multi-objective Mixer model for balanced, safe and robust prediction in medicinecited by 1
  6. 2022A Novel Explainable Out-of-Distribution Detection Approach for Spiking Neural Networkscited by 1
  7. 2022Towards Generating Adversarial Examples on Mixed-type Datacited by 1
  8. 2021Out of distribution detection for skin and malaria imagescited by 0
  9. 2023Uncertainty in AI: Evaluating Deep Neural Networks on Out-of-Distribution Imagescited by 0
  10. 2024Adversarial Detection with a Dynamically Stable Systemcited by 0