arXiv Machine Learning By Jong-Ik Park, Shreyas Chaudhari, Carlee Joe-Wong, Jos\'e M. F. Moura

RRISE: Robust Radius Inference via a Surrogate Estimator

Read the original on arXiv Machine Learning →

arXiv:2606. 02876v1 Announce Type: new Abstract: Randomized smoothing (RS) uses a smoothed classifier to provide architecture-agnostic certificates of $\ell_2$ classification robustness, but its dependence on per-input Monte Carlo (MC) sampling undermines its use in real-time systems.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI
Jun 29

Halt Fast! Early Stopping for Certified Robustness

arXiv:2606. 27694v1 Announce Type: cross Abstract: Randomized Smoothing (RS) provides rigorous robustness guarantees for neural networks without architectural constraints, yet its adoption is limited by extreme computational costs.

By Andrew C. Cullen, Paul Montague, Benjamin I. P. Rubinstein
arXiv Machine Learning
6d ago

Linear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured Prediction

arXiv:2604. 27742v2 Announce Type: replace Abstract: A fundamental dichotomy in the theory of classification sets smoothness against statistical efficiency: smooth surrogate losses such as the logistic loss enable fast $O(1/T)$ optimization but yield slow square-root $H$-consistency bounds, while piecewise-linear losses like the Hinge loss achieve optimal linear $H$-consistency rates but are non-differentiable.

By Mehryar Mohri, Yutao Zhong
arXiv Machine Learning
Aug 4

Caliber: Cross-Architecture Extraction-Cost Control for Score-Returning APIs

arXiv:2608. 01023v1 Announce Type: new Abstract: We present Caliber, an output-perturbation defense against model extraction that formulates noise selection as a calibration problem: how much the defense degrades the supervision signal used to train a surrogate, and the provable per-input query cost of recovering the clean logits.

By Chi Wang, Hanwen Wang, Yu Xia, Zihan Wang, Guangdong Bai