Robustness Meets Uncertainty: Evidential Adversarial Training for Robust Selective Classification

• URL: http://arxiv.org/abs/2607.03075v1
• Date: Fri, 03 Jul 2026 08:10:21 GMT
• Title: Robustness Meets Uncertainty: Evidential Adversarial Training for Robust Selective Classification
• Abstract summary: Adversarial training is a widely adopted defense for improving robustness in deep neural networks.<n>We introduce a unified benchmark for the robustness-uncertainty trade-off.<n>Evidential Adversarial Training (EV-AT) 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.
• Score: 26.819297652576967
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 https://github.com/NicolasSournac/Robustness_Meets_Uncertainty.EV-AT.

Related papers

• Socrates Loss: Unifying Confidence Calibration and Classification by Leveraging the Unknown [4.503897051444244]
  Deep neural networks, despite their high accuracy, often exhibit poor confidence calibration, limiting their reliability in high-stakes applications.<n>Current ad-hoc confidence calibration methods attempt to fix this during training but face a fundamental trade-off.<n>This paper addresses and mitigates this stability-performance trade-off.<n>We propose Socrates Loss, a novel, unified loss function that explicitly leverages uncertainty by incorporating an auxiliary unknown class.
  arXiv  Detail & Related papers  (2026-04-14T03:43:15Z)
• Calibrating Uncertainty for Zero-Shot Adversarial CLIP [33.707647228637114]
  We propose a novel adversarial fine-tuning objective for CLIP considering both prediction accuracy and uncertainty alignments.<n>Our objective aligns these distributions holistically under perturbations, moving beyond single-logit anchoring and restoring uncertainty.
  arXiv  Detail & Related papers  (2025-12-15T05:41:08Z)
• The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks [90.52808174102157]
  In safety-critical applications such as medical imaging and autonomous driving, it is imperative to maintain both high adversarial robustness to protect against potential adversarial attacks. A notable knowledge gap remains concerning the uncertainty inherent in adversarially trained models. This study investigates the uncertainty of deep learning models by examining the performance of conformal prediction (CP) in the context of standard adversarial attacks.
  arXiv  Detail & Related papers  (2024-05-14T18:05:19Z)
• Revisiting Confidence Estimation: Towards Reliable Failure Prediction [53.79160907725975]
  We find a general, widely existing but actually-neglected phenomenon that most confidence estimation methods are harmful for detecting misclassification errors. We propose to enlarge the confidence gap by finding flat minima, which yields state-of-the-art failure prediction performance.
  arXiv  Detail & Related papers  (2024-03-05T11:44:14Z)
• Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off [11.836020809561383]
  Adversarial training often suffers from a robustness-accuracy trade-off, where achieving high robustness comes at the cost of accuracy.<n>We propose Asymmetric Representation-regularized Adversarial Training (ARAT)<n>ARAT incorporates asymmetric invariance loss with stop-gradient operation and a predictor to avoid gradient conflict, and a split-BatchNorm (BN) structure to resolve the mixture distribution problem.
  arXiv  Detail & Related papers  (2024-02-22T15:53:46Z)
• Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-Off [107.35833747750446]
  adversarial examples can be crafted by adding imperceptible perturbations to legitimate documents. This vulnerability raises significant concerns about their reliability and hinders the widespread deployment of NRMs. In this study, we establish theoretical guarantees regarding the effectiveness-robustness trade-off in NRMs.
  arXiv  Detail & Related papers  (2023-12-16T05:38:39Z)
• Towards Certified Probabilistic Robustness with High Accuracy [3.957941698534126]
  Adrial examples pose a security threat to many critical systems built on neural networks. How to build certifiably robust yet accurate neural network models remains an open problem. We propose a novel approach that aims to achieve both high accuracy and certified probabilistic robustness.
  arXiv  Detail & Related papers  (2023-09-02T09:39:47Z)
• A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking [54.89987482509155]
  robustness of deep neural networks is usually lacking under adversarial examples, common corruptions, and distribution shifts. We establish a comprehensive benchmark robustness called textbfARES-Bench on the image classification task. By designing the training settings accordingly, we achieve the new state-of-the-art adversarial robustness.
  arXiv  Detail & Related papers  (2023-02-28T04:26:20Z)
• Adversarial Robustness under Long-Tailed Distribution [93.50792075460336]
  Adversarial robustness has attracted extensive studies recently by revealing the vulnerability and intrinsic characteristics of deep networks. In this work we investigate the adversarial vulnerability as well as defense under long-tailed distributions. We propose a clean yet effective framework, RoBal, which consists of two dedicated modules, a scale-invariant and data re-balancing.
  arXiv  Detail & Related papers  (2021-04-06T17:53:08Z)
• Adversarial Robustness on In- and Out-Distribution Improves Explainability [109.68938066821246]
  RATIO is a training procedure for robustness via Adversarial Training on In- and Out-distribution. RATIO achieves state-of-the-art $l$-adrial on CIFAR10 and maintains better clean accuracy.
  arXiv  Detail & Related papers  (2020-03-20T18:57:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.