arXiv Machine Learning July 10, 2026 By Rodrigo F. L. Lassance, Jasper De Bock

Robustness Quantification for Discriminative Models: a New Robustness Metric and its Application to Dynamic Classifier Selection

Read the original on arXiv Machine Learning →

arXiv:2603. 23318v2 Announce Type: replace Abstract: Among the different possible strategies for evaluating the reliability of individual predictions of classifiers, robustness quantification stands out as a method that evaluates how much uncertainty a classifier could cope with before changing its prediction.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 2

Sensitivity as a Double-Edged Sword: A Trade-off Between Discriminability and Adversarial Robustness

arXiv:2606. 01746v1 Announce Type: cross Abstract: Modern neural networks are highly susceptible to adversarial perturbations.

By Kai Wang

fine-tuning benchmarks safety

arXiv Machine Learning

Jul 7

Robustness Meets Uncertainty: Evidential Adversarial Training for Robust Selective Classification

arXiv:2607. 03075v1 Announce Type: new Abstract: Safety-critical applications require classifiers that are both robust and reliable.

By Nicolas Sournac, Ahmed Baha Ben Jmaa, Bertrand Braeckeveldt

benchmarks safety

arXiv Machine Learning

Jul 9

Optimized Instance Alteration for Explaining and Assessing Robustness of Classifiers

arXiv:2607. 06637v1 Announce Type: new Abstract: In this work, we propose a unified approach for diagnosing misclassification and assessing the robustness of black-box classifiers.

By Evgenii Kuriabov, David Miller, Jia Li

safety

arXiv Machine Learning

Jul 8

Higher-Order Certified Robustness for Regression

arXiv:2607. 05536v1 Announce Type: cross Abstract: Randomized smoothing has emerged as a scalable technique for certifying the adversarial robustness of classifiers.

By Jie Zhang, Natalie Frank

benchmarks safety

OpenAI Blog

Feb 4, 2019

Computational limitations in robust classification and win-win results

arXiv AI

Jul 15

Quantification of Credal Uncertainty: A Distance-Based Approach

arXiv:2603. 27270v2 Announce Type: replace Abstract: Credal sets, i.

By Xabier Gonzalez-Garcia, Siu Lun Chau, Julian Rodemann, Michele Caprio, Krikamol Muandet, Humberto Bustince, S\'ebastien Destercke, Eyke H\"ullermeier, Yusuf Sale

Related stories

Sensitivity as a Double-Edged Sword: A Trade-off Between Discriminability and Adversarial Robustness

Robustness Meets Uncertainty: Evidential Adversarial Training for Robust Selective Classification

Optimized Instance Alteration for Explaining and Assessing Robustness of Classifiers

Higher-Order Certified Robustness for Regression

Computational limitations in robust classification and win-win results

Quantification of Credal Uncertainty: A Distance-Based Approach