pith. sign in

arXiv preprint arXiv:2004.01832 , year=

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.LG 2

years

2026 2

verdicts

UNVERDICTED 2

clear filters

representative citing papers

SORA: Free Second-Order Attacks in Fast Adversarial Training

cs.LG · 2026-05-30 · unverdicted · novelty 5.0

SORA is an adaptive step-size adversarial training algorithm that formalizes epsilon overfitting, introduces the PertAlign metric to predict catastrophic overfitting, and dynamically adjusts perturbations to achieve state-of-the-art robustness and clean accuracy with fixed hyperparameters.

citing papers explorer

Showing 2 of 2 citing papers after filters.

  • SORA: Free Second-Order Attacks in Fast Adversarial Training cs.LG · 2026-05-30 · unverdicted · none · ref 44

    SORA is an adaptive step-size adversarial training algorithm that formalizes epsilon overfitting, introduces the PertAlign metric to predict catastrophic overfitting, and dynamically adjusts perturbations to achieve state-of-the-art robustness and clean accuracy with fixed hyperparameters.

  • Margin-Adaptive Confidence Ranking for Reliable LLM Judgement cs.LG · 2026-05-14 · unverdicted · none · ref 145

    Develops a margin-adaptive learned confidence estimator for LLMs with generalization guarantees to improve agreement rates with human judgments over heuristic baselines.