arXiv Machine Learning October 19, 2026 By Rachel Morris, Ryan Murray, Kerrek Stinson

On the tradeoff between robustness and geometric accuracy in adversarial training

Read the original on arXiv Machine Learning →

arXiv:2610. 22955v1 Announce Type: new Abstract: For non-parametric binary classification in the presence of an adversary, we prove an optimal quantitative estimate for adversarial classifiers controlling geometric accuracy, as measured by the Hausdorff distance to the Bayes classifier, in terms or their robustness, as encoded by the adversarial budget $\varepsilon$.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

safety

arXiv AI

Oct 1

Probabilistic Adversarial Training

The paper introduces probabilistic adversarial training, a method that enhances robustness by reducing the overlap between a distance-based distribution and a victim-classifier-induced distribution. It derives a KL-based lower bound on probabilistic robustness, which serves as a tractable surrogate objective. Experiments confirm that this approach consistently improves probabilistic robustness and can even boost non-probabilistic adversarial training methods through an induced scaling factor.

By Andi Zhang, Xingyu Zhao, Siddartha Khastgir

benchmarks safety

arXiv Machine Learning

Jul 7

Robustness Meets Uncertainty: Evidential Adversarial Training for Robust Selective Classification

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

benchmarks safety

arXiv Machine Learning

Sep 2

On the Existence of Consistent Adversarial Attacks in High-Dimensional Linear Classification

arXiv:2506.12454v2 Announce Type: replace-cross Abstract: What fundamentally distinguishes an adversarial attack from a misclassification due to limited model expressivity or finite data? In this wor...

By Matteo Vilucchio, Lenka Zdeborov\'a, Bruno Loureiro

diffusion safety

arXiv Machine Learning

Jun 2

A unifying Bayesian framework for adversarial robustness

arXiv:2510. 09288v2 Announce Type: replace-cross Abstract: The vulnerability of machine learning models to adversarial attacks remains a critical societal security challenge.

By Pablo G. Arce, Roi Naveiro, David R\'ios Insua

benchmarks safety

Hugging Face Trending Papers

Sep 21

Adversarially Robust PAC Learning with Optimal VC Rates

We study the problem of \emph{adversarially robust} PAC learning. In this framework, the learner observes independent samples from an unknown distribution over $\mathcal{X} \times \{0,1\}$, as in clas...

safety

arXiv Machine Learning

6d ago

Deterministic Bounds on Accuracy and Stability of Metric-Space Regression and Classification

arXiv:2610.22564v1 Announce Type: new Abstract: Data-driven approaches often face ambiguity in datasets due to sensor or target noise, insufficient information, and noise in the input data. While bes...

By Nina Maria Gottschling, Jakob Gawlikowski, Michele Caprio

One email a morning, machine-written

Related stories

Probabilistic Adversarial Training

Robustness Meets Uncertainty: Evidential Adversarial Training for Robust Selective Classification

On the Existence of Consistent Adversarial Attacks in High-Dimensional Linear Classification

A unifying Bayesian framework for adversarial robustness

Adversarially Robust PAC Learning with Optimal VC Rates

Deterministic Bounds on Accuracy and Stability of Metric-Space Regression and Classification