AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

Robustness Meets Uncertainty: Evidential Adversarial Training for Robust Selective Classification

Nicolas Sournac, Ahmed Baha Ben Jmaa, Bertrand Braeckeveldt

ECCV 2026 · Adversarial robustness and security › Certified and empirical robustness · approach: Robustness-accuracy trade-off analysis · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add robust evidence alignment (beta>0) (ablation)EV-AT · CIFAR-10 WRN-34-10 AugMixClean/AA accuracy: 20.11 -> 71.51Improved
add robust evidence alignment (beta>0) (ablation)EV-AT · CIFAR-10 WRN-34-10 AugMixClean/AA AUGRC: 37.67 -> 6.67Improved
add AWP (ablation)EV-AT · CIFAR-10 WRN-34-10 AugMixClean/AA accuracy: 68.46 -> 71.51Improved
add AWP (ablation)EV-AT · CIFAR-10 WRN-34-10 AugMixClean/AA AUGRC: 8.21 -> 6.67Improved
use evidential clean loss instead of cross-entropy (ablation)EV-AT · CIFAR-10 WRN-34-10 AugMixClean/AA accuracy: 69.56 -> 71.51Improved
use evidential clean loss instead of cross-entropy (ablation)EV-AT · CIFAR-10 WRN-34-10 AugMixClean/AA AUGRC: 7.88 -> 6.67Improved
align in log alpha instead of alpha (ablation)EV-AT · CIFAR-10 WRN-34-10 AugMixClean/AA accuracy: 67.32 -> 71.51Improved
align in log alpha instead of Dirichlet mean (ablation)EV-AT · CIFAR-10 WRN-34-10 AugMixClean/AA AUGRC: 10.43 -> 6.67Improved
use IKL instead of KL for REA divergence (ablation)EV-AT · CIFAR-10 WRN-34-10 AugMixClean/AA accuracy: 70.61 -> 71.51Improved
use IKL instead of L2 for REA divergence (ablation)EV-AT · CIFAR-10 WRN-34-10 AugMixClean/AA AUGRC: 7.64 -> 6.67Improved
use IKL instead of CE in inner maximization (ablation)EV-AT · CIFAR-10 WRN-34-10 AugMixClean/AA AUGRC: 6.38 vs 6.67Mixed
use IKL instead of KL in inner maximization (ablation)EV-AT · CIFAR-10 WRN-34-10 AugMixClean/AA accuracy: 71.52 vs 71.51No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy