conftrace_

certification framework

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

hellinger distance (1) gradient training (1) black-box model (1) out-of-domain generalization (1) distributional robustness (1) machine unlearning (1) data poisoning (1) differential privacy (1)

Papers

Abstract Gradient Training: A Unified Certification Framework for Data Poisoning, Unlearning, and Differential Privacy JMLR 2026 Certifying Out-of-Domain Generalization for Blackbox Functions ICML 2022