Adversarially robust learning could leverage computational hardness.

MaRDI QIDQ7025138zbMATH OpenFDO

Authors Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mahmoody Mohammad

Publication date 19 February 2025

Full work available at URL https://proceedings.mlr.press/v117/garg20a.html

zbMATH Keywords

robust learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• Adaptive One-Way Functions and Applications
• Advances in Cryptology - CRYPTO 2003
• Asymptotic theory of finite dimensional normed spaces. With an appendix by M. Gromov: Isoperimetric inequalities in Riemannian manifolds
• Can adversarially robust learning leverage computational hardness?
• Cryptographic assumptions: a position paper
• General hardness amplification of predicates and puzzles. (Extended abstract)
• scientific article; zbMATH DE number 7014202 (Why is no real title available?)
• Probably approximately correct. Nature's algorithms for learning and prospering in a complex world
• Simplifying game-based definitions -- indistinguishability up to correctness and its application to stateful AE
• The concentration of measure phenomenon
• Theory of Cryptography

This page was built for publication: Adversarially robust learning could leverage computational hardness.

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7025138)