Robustness Meets Uncertainty: Evidential Adversarial Training for Robust Selective Classification
Summary
This paper introduces Evidential Adversarial Training (EV-AT), a method that improves the robustness-uncertainty trade-off in classifiers by combining an evidence-based loss with robust evidence alignment, achieving state-of-the-art results on selective classification benchmarks.
View Cached Full Text
Cached at: 07/07/26, 04:40 AM
# Robustness Meets Uncertainty: Evidential Adversarial Training for Robust Selective Classification Source: [https://arxiv.org/abs/2607.03075](https://arxiv.org/abs/2607.03075) [View PDF](https://arxiv.org/pdf/2607.03075) > Abstract:Safety\-critical applications require classifiers that are both robust and reliable\. Adversarial training is a widely adopted defense for improving robustness in deep neural networks; however, its effect on the reliability of predictive uncertainty remains underexplored\. We investigate this gap through the lens of selective classification, which has rarely been systematically analyzed alongside adversarial robustness\. We introduce a unified benchmark for the robustness\-uncertainty trade\-off\. It standardizes architectures, augmentations, threat models, and evaluation metrics across clean, adversarial, and common\-corruption settings\. Across a wide range of state\-of\-the\-art adversarial training methods, we uncover a recurring failure mode: several approaches improve robust accuracy while degrading uncertainty ranking, leading to poorer selective behavior\. To address this, we propose Evidential Adversarial Training \(EV\-AT\), which models uncertainty through a Dirichlet distribution and combines \(i\) an evidence\-based loss promoting clean accuracy and reliable uncertainty with \(ii\) a robust evidence\-alignment loss matching clean and adversarial predictions in log Dirichlet\-parameter space\. Extensive experiments show that EV\-AT shifts the Pareto frontier of robustness\-uncertainty trade\-offs beyond prior state\-of\-the\-art adversarial training methods\. Our source code is publicly available at[this https URL](https://github.com/NicolasSournac/Robustness_Meets_Uncertainty.EV-AT)\. ## Submission history From: Nicolas Sournac \[[view email](https://arxiv.org/show-email/377bd7be/2607.03075)\] **\[v1\]**Fri, 3 Jul 2026 08:10:21 UTC \(1,592 KB\)
Similar Articles
UASPL: Uncertainty-Aware Self-Paced Learning with Evidential Neural Networks
The paper proposes UASPL, a method that integrates predictive reliability into sample selection for self-paced learning using evidential neural networks, improving classification performance and interpretability.
Streaming Adversarial Robustness in Fuzzy ARTMAP: Mechanism-Aligned Evaluation, Progressive Training, and Interpretable Diagnostics
This paper investigates adversarial robustness in Fuzzy ARTMAP, a streaming neural architecture, by introducing WB-Softmax as a mechanism-aligned white-box attack surrogate. It evaluates progressive training and selective updating strategies to improve robustness without data replay, while also offering interpretable diagnostics for structural failures.
Reducing information dependency does not cause training data privacy. Adversarially non-robust features do
This paper challenges the prevailing view that rote memorization causes training data exposure to reconstruction attacks, showing instead that adversarial non-robust features are the true cause. The authors introduce AntiAdversarial Training (AT-AT) that intentionally learns non-robust features to achieve superior reconstruction defense and higher accuracy.
Halt Fast! Early Stopping for Certified Robustness
This paper introduces a meta-learning framework for anytime-valid certified robustness that uses sequential E-processes to adaptively allocate compute, achieving a 20-fold reduction in sample complexity compared to traditional randomized smoothing while maintaining rigorous statistical guarantees.
Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models
This paper introduces a compute-aware evaluation framework for adversarial robustness of LLMs, proposing risk-compute curves and metrics based on FLOPs to better assess attack costs, finding that alignment training has non-monotonic effects and compute costs vary across models and harm categories.