PAC-learning in the presence of adversaries

Daniel Cullina, Arjun Nitin Bhagoji, Prateek Mittal

Feb-13-2026, 17:17:28 GMT–Neural Information Processing Systems

Intheadversarialsetting,weintroduce the notion ofadversarial VC-dimensionwhich is the VC-dimension of the corrupted hypothesis class.

artificial intelligence, arxivpreprintarxiv, machine learning, (18 more...)

Neural Information Processing Systems

Feb-13-2026, 17:17:28 GMT

Conferences PDF

Country:
- North America
  - Canada (0.04)
  - United States (0.14)

Technology:
- Information Technology > Artificial Intelligence > Machine Learning
  - Computational Learning Theory (0.52)
  - Statistical Learning (0.46)