Adversarial attacks on Learning-to-Defer routers are formalized, and a convex robust surrogate loss, SARD, is proposed with empirical robustness gains and incomplete consistency guarantees.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees
Adversarial attacks on Learning-to-Defer routers are formalized, and a convex robust surrogate loss, SARD, is proposed with empirical robustness gains and incomplete consistency guarantees.