The paper introduces techniques for measuring the robustness of predictions made by two generative classifiers—naive Bayes classifiers and generative forests—whose underlying models are probabilistic graphical models. Robustness is defined as the degree to which the classifier’s distribution can be perturbed without altering its prediction, with perturbations explored via epsilon‑contamination, total variation distance, and chi‑squared divergence neighborhoods. Experiments on benchmark datasets show that the computed robustness values can serve as indicators of prediction trustworthiness and are compared against other existing indicators.
By Adri\'an Detavernier, Jasper De Bock
arXiv:2606. 01746v1 Announce Type: cross Abstract: Modern neural networks are highly susceptible to adversarial perturbations.
By Kai Wang
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
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
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
The paper demonstrates that common binary classification metrics—Matthews' correlation coefficient, Cohen's κ, the F-score, and the Jaccard similarity—are not robust to extreme class imbalance, as the Bayes classifier’s true positive rate tends to zero when the minority class proportion vanishes. To address this, the authors propose robustified versions of these metrics that include a tuning parameter, ensuring that the Bayes-optimal classifier’s threshold remains bounded and its true positive rate stays above zero even in highly imbalanced scenarios. The study provides theoretical bounds, simulation results, and practical guidance on applying these robust metrics to real data, such as a credit‑default dataset, and discusses their relationship to ROC and precision‑recall curves.
By Hajo Holzmann, Bernhard Klar
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
arXiv:2505. 08784v2 Announce Type: replace-cross Abstract: As machine learning (ML) enters high-stakes domains, trustworthy uncertainty quantification (UQ) is essential for safety.
By Abhineet Agarwal, Fange Xiao, Rebecca Barter, Omer Ronen, Boyu Fan, Bin Yu
arXiv:2602. 07453v2 Announce Type: replace Abstract: Decision tree ensembles are widely used in critical domains, making robustness and sensitivity analysis essential to their trustworthiness.
By Namrita Varshney, Ashutosh Gupta, Arhaan Ahmad, Tanay V. Tayal, S. Akshay
The paper introduces the Latent Diagnostic Taxonomy, a framework that builds a dimensionality‑optimized classifier and a diagnostic tool to assess the trustworthiness of its confident predictions. It identifies a small set of influential prompts (latent support vectors) that reveal tokens which can change the classifier’s output, and uses these tokens to create a taxonomy that classifies prompts into safe, heuristic bias, heuristic override, or insufficient context categories. Applied to a prompt‑injection detection model, the framework shows that about 77% of confident decisions are fragile to a single token, distinguishing between calibration failures and exploitable shortcuts, and offers remediation strategies for each taxonomy zone.
By Jaturong Kongmanee, Smile Thanapattheerakul
arXiv:2608. 11541v1 Announce Type: new Abstract: Machine learning models should be robust, in the sense of remaining predictively consistent under permissible variations.
By Manya Singh, Mark T. Keane, Arjun Pakrashi